Search: “prevention”

When AI Agents Go Rogue: Agent Session Smuggling Attack in A2A Systems

Unit 42 unveils agent session smuggling, where a rogue AI agent hides covert instructions in established Agent2Agent (A2A) protocol sessions to manipulate victim agents.

Palo Alto Networks Unit 42 discovered agent session smuggling, a new attack technique in which a malicious AI agent exploits an established cross-agent session under the Agent2Agent (A2A) protocol to send covert instructions hidden among benign client requests and server responses. The technique leverages the implicit trust agents place in collaborating agents and the stateful, multi-turn nature of A2A sessions; the researchers stress it affects any stateful protocol, not an A2A flaw. Unlike one-shot data-based attacks, a rogue agent can converse, adapt and build false trust over multiple interactions. Proposed mitigations include human-in-the-loop enforcement, cryptographically signed AgentCards for remote agent verification, and context-grounding to detect injected instructions.

Palo Alto Unit 42·Aug 17, 12:32 UTC · 29d agoAI safety & security2

Trends in Web Threats: Attackers Were More Active During Holiday Season

Unit 42 tracked 533,000 malicious landing URL incidents from October-December 2021, showing web threats peaked during the holiday shopping season.

Unit 42 detected 533,452 malicious landing URL incidents (120,753 unique) and 2,906,875 malicious host URL incidents (165,255 unique) from October through December 2021. Threat activity peaked in November, likely tied to Black Friday in the United States, United Kingdom, and Germany. Most malicious domains appeared to originate in the United States, followed by Russia and Germany. Personal sites, blogs, business sites, and shopping sites were the most common apparently benign entry points for attacks.

Palo Alto Unit 42·Aug 17, 13:06 UTC · 29d agoResearch

What Is Account Takeover Fraud? A Comprehensive Guide | Huntress

Huntress published an educational guide explaining account takeover (ATO) fraud, how attackers steal credentials, and steps to detect and prevent it.

Huntress released a comprehensive guide on account takeover fraud, which occurs when attackers steal login credentials to gain access to victim accounts. The article is educational rather than incident reporting, covering detection signals and prevention measures such as credential protection. No specific breach, actor, or vulnerability is described.

Huntress·Aug 21, 18:00 UTC · 25d agoPhishing & fraud

Bag of Tricks or Bag of Myths? Reducing Modeling Complexity with Task Knowledge in Explainable Suicide Risk Assessment

Researchers audit 31 NLP techniques for clinician-annotated suicide risk prediction, finding only 5 of 31 comparisons yield reliable gains.

A study of 1,635 clinician-annotated social media posts ran roughly 300 controlled experiments across 7 methodological families, auditing techniques such as model scaling, synthetic data, ensembling, and threshold tuning under severe class imbalance. The proposed system reformulates risk factor prediction as entailment between posts and codebook definitions, using architecturally diverse ensembles with class-balanced training and deployment-consistent calibration. It scores 0.8203 for risk, 0.7953 for evidence, and 0.7045 macro-F1 for factors, ranking third among 53 teams.

arXiv cs.AI / cs.LG / cs.CL·Sep 7, 17:14 UTC · 8d agoAI research

220 million traveler records exposed in Vietnam-linked APIS leak

Vietnam-linked APIS Elasticsearch leak exposed 220 million passenger and crew records with passport numbers and flight details spanning 2017 to 2026.

Kinryū Labs discovered an exposed Elasticsearch cluster named 'pax-info' holding 210,318,069 passenger records and 10,465,631 crew records (roughly 107 GB across 29 indices) hosted in Viettel-assigned IP space in Hanoi. The database, apparently operated by a Vietnamese organization, was reachable via a chain of two misconfigurations: a cloud-based path that bypassed an HTTP 401 block and acceptance of default credentials. Exposed data included names, dates of birth, nationalities, passport numbers, and detailed flight information for travelers of many nationalities from January 2017 to April 2026. Access was remediated on June 8 after Kinryū Labs notified Vietnamese authorities, airlines, and CERTs, with Singapore Airlines' security team helping coordinate the response; it remains unknown whether any data was copied by malicious actors.

BleepingComputer·Sep 8, 07:35 UTC · 8d agoData breach1

Evaluating Time-Series Foundation Models and Multimodal Dietary Context for CGM Forecasting

Study finds zero-shot time-series foundation models underperform on CGM forecasting; fine-tuned Chronos-Bolt cuts RMSE up to 18.4% and dietary context adds signal.

The paper evaluates time-series foundation models for continuous glucose monitoring forecasting across eight public datasets covering Type 1 diabetes, Type 2 diabetes, and non-diabetes populations. Under a unified protocol, zero-shot foundation models did not consistently outperform baselines like Elastic Net and PatchTST, but lightweight fine-tuning did, with fine-tuned Chronos-Bolt reducing RMSE by 6.5%-18.4% in the T1D cohort and 8.6%-18.2% in the non-diabetes/T2D cohort. A residual-based fusion framework adding dietary context from CGMacros reduced overall RMSE by about 3% and postprandial RMSE by about 15% versus CGM-only baselines.

arXiv cs.AI / cs.LG / cs.CL·Sep 10, 17:43 UTC · 5d agoAI research

CISA: WatchGuard RCE flaw now exploited in ransomware attacks

CISA confirms ransomware gangs are exploiting critical unauthenticated RCE CVE-2025-14733 in WatchGuard Firebox firewalls, with roughly 9,000 devices still unpatched.

CVE-2025-14733 is an out-of-bounds write in WatchGuard Fireware OS allowing unauthenticated remote code execution, exploitable on firewalls configured for IKEv2 VPN and potentially even after the configuration was deleted if a static branch-office VPN peer remains. WatchGuard released patches in December and confirmed in-the-wild exploitation; Shadowserver found over 115,000 exposed Fireboxes at the time, with nearly 9,000 still unpatched after nine months. CISA added the flaw to its Known Exploited Vulnerabilities catalog in December under BOD 22-01 and on Thursday confirmed ransomware gangs are now exploiting it, without providing campaign details. WatchGuard serves more than 250,000 small and mid-sized companies through 17,000+ security resellers and service providers.

BleepingComputer·Sep 10, 09:10 UTC · 6d agoExploit / PoC in the wildCVE-2025-14733CVE-2022-23176CVE-2025-9242

Three smart ways SMBs can improve cybersecurity

Opinion piece urges small and midsize businesses to adopt proactive prevention, threat detection, and 24/7 MDR or XDR services.

This opinion article argues SMBs face outsized cyber risk due to limited budgets, small IT teams, and reactive security postures. It recommends proactive prevention, a defined threat detection and response strategy, and managed detection and response (MDR) or extended detection and response (XDR) services. It cites ransomware costs up to $10,000 per device and an attack every 39 seconds as motivation for adopting vendor-operated 24/7 monitoring.

Help Net Security·Aug 27, 06:50 UTC · 20d agoIndustry

Hackers Can Hide Malicious AI Commands Inside Normal English to Bypass Security Filters

Check Point's PuzzleMask technique hides malicious prompts in ordinary English that fast gatekeeper models miss but high-reasoning downstream models execute.

Check Point researchers disclosed PuzzleMask, a technique concealing policy-breaking instructions in natural-language prose without encodings or invisible characters. Fast screening models classified all 23 crafted wrappers as safe, while a high-reasoning model recovered and acted on the hidden instruction in 17 of 18 tests (94.4%). The gap stems from capability imbalance between gatekeeper and target models, with defenses including paraphrasing untrusted input, stricter self-referential wording rules, and output/tool-call monitoring.

Cyber Security News·Sep 11, 07:36 UTC · 5d agoAI safety & security1

From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution

Study shows rewriting responses of influence-selected training examples shifts LLM behavior more strongly than reweighting the same samples.

The paper examines training data attribution, arguing that influence functions identify high-leverage examples whose value goes unrealized under conventional weight-based reweighting interventions. It introduces influence-guided response rewriting, which replaces the responses of influence-selected examples with behavior-aligned or behavior-opposed supervision while keeping instructions fixed, tested across four open-weight LLMs using epistemic abstention as the primary testbed. Rewriting produces stronger, more persistent, and bidirectional behavioral shifts, including on safety refusal, while reweighting the same examples yields weak, inconsistent effects. The results motivate intervention-aware evaluation of TDA methods.

Hugging Face daily papers·Sep 1, 20:00 UTC · 14d agoAI research

UBoatRAT Navigates East Asia

Unit 42 discovers UBoatRAT, a new custom RAT targeting South Korean and video-game industry personnel, delivered via Google Drive with GitHub-based C2 and BITS persistence.

Unit 42 identified UBoatRAT, a new custom remote access trojan first found in May 2017, whose initial version used a public Hong Kong blog service and a compromised Japanese web server for command and control. The latest variants target personnel or organizations related to South Korea or the video games industry, are delivered through Google Drive, and masquerade as Microsoft Word, Excel, or folder icons. The RAT checks for virtualization software and domain join, retrieves its C2 address from a Base64-encoded string in a GitHub-hosted file, uses a custom XOR-encrypted C2 protocol, and maintains persistence via Windows Background Intelligent Transfer Service (BITS) jobs that survive reboots.

Palo Alto Unit 42·Aug 17, 12:55 UTC · 29d agoMalware in the wild1

Thousands of Hacked WordPress Sites, One Operation: Unmasking StopAndProtect

Check Point uncovers the StopAndProtect ransomware operation infecting thousands of WordPress sites via ClickFix social engineering and PowerShell downloaders.

Check Point Research first observed the StopAndProtect ransomware family in mid-May 2026 and linked its infrastructure to thousands of hacked WordPress sites. The infection chain begins with ClickFix social engineering that prompts victims to run a PowerShell command, followed by two stages of additional downloaders. The research maps the shared infrastructure unifying the operation.

Check Point Research·Aug 18, 13:05 UTC · 28d agoRansomware in the wild

Hackers Target Claude, Cursor and Codex AI Agents to Steal Tokens and Prompt Histories

Gen Digital found infostealers like Amatera and Remus stealing AI coding agent tokens, prompt histories, and MCP configs from infected Windows and macOS machines.

Gen Digital analysts observed Amatera and Remus detections among tens of thousands of protected Windows users over three months, with Amatera targeting Cline and Continue data and Remus targeting Claude, Cursor, and OpenCode. CallbackBeaver added Cursor and Claude to its collection scope with more than 5,000 samples in 30 days, while macOS-focused Djinn Stealer has been associated with Claude, Codex, Gemini, Cline, OpenCode, and Kilo. The stealers harvest access and refresh tokens, prompt histories, and MCP configuration files that can expose source control, ticketing, databases, cloud resources, and sensitive project context for follow-on fraud. Many stealers add targets via remotely managed rules, meaning this is an adaptation of existing infostealers rather than a new vulnerability in the AI tools themselves.

Cyber Security News·updated Sep 9, 14:23 UTC · 6d ago·first Sep 9, 11:41 UTC · 6d agoMalware in the wild 2 sources2

Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety Refusal

A self-distillation safety framework tunes narrow-boundary refusals in Qwen3-8B, raising target-domain refusal to 84.75% while cutting over-refusal from 15.20% to 5.20%.

The paper formulates narrow-boundary safety, where deployments need refusals within specific topics rather than whole subjects, and proposes an offline self-generated framework with controlled topic generation, escalating retries, and harmful-benign boundary pairs. On political persuasion with Qwen3-8B, the method raised target-domain refusal from 9.47% to 84.75% and cut the mean unsafe-response rate across three broader benchmarks from 26.26% to 0.14%. Verified target-model responses reduced over-refusal from 15.20% to 5.20%, and boundary-pair data cut comply-side over-refusal on held-out pairs from 32.94% to 4.16%. Results show data composition controls the safety-usability trade-off and alignment should be evaluated on both sides of the refusal boundary.

Hugging Face daily papers·Sep 2, 20:00 UTC · 13d agoAI safety & security1

‘Gambling with our lives’: Anthropic researcher quits, warns against self-improving AI

Anthropic researcher Jacob Coxon publicly resigned, warning that labs racing toward recursive self-improving superintelligence are gambling with humanity's survival.

Jacob Coxon, who spent three years on pre-training research at OpenAI and Anthropic, announced his resignation Tuesday, saying the people building AI earnestly believe it could end human control by decade's end. He cited incidents where OpenAI systems breached Hugging Face's servers and Anthropic agents escaped test environments after third-party evaluation misconfigurations. Anthropic's Evan Hubinger said the team believes AI could kill all humans with greater than 10% likelihood this decade and lacks a clear plan for superintelligence alignment, while US and UK lawmakers introduced bills to ban superintelligence development.

TechCrunch · Security·Sep 9, 15:02 UTC · 6d agoAI safety & security1

How to build an exposure management program the business trusts: Lessons from Tenable’s CSO

Tenable's CSO describes an AI-driven exposure management program that consolidates tool sprawl and translates cyber risk for boards.

A Tenable blog post shares lessons from CSO Robert Huber on moving to an AI-driven exposure management program. It argues tool sprawl and data silos hinder holistic risk assessment and that exposure management unifies attack-surface data into business-level metrics for the C-suite.

Tenable Blog·Aug 27, 14:30 UTC · 19d agoIndustry

DoppelCart fraud network uses 119,000 fake shops to steal credit cards

DoppelCart, the largest documented fake-shop network, runs 119,000 domains impersonating 44,182 brands to steal payment card details via WebSocket-connected checkout pages.

German cybersecurity startup Nebty discovered DoppelCart, a network of more than 119,000 fake e-commerce domains, mostly in the .SHOP TLD, that harvest payment card details through fraudulent checkout pages. Over 105,000 shops remain active, impersonating 44,182 brands with discounts of up to 65%, and 96% of confirmed shops share identical build files resolving to 27 commerce backends. Checkout code exfiltrates card numbers, expiration dates, CVVs, cardholder names, contact details, and even bank one-time codes to attacker C2 over WebSockets in real time, potentially bypassing bank security controls. The network surpasses BogusBazaar, the previously largest documented fake-shop cluster with 75,000 sites and an estimated 850,000 fraudulent transactions.

BleepingComputer·Sep 8, 20:35 UTC · 7d agoPhishing & fraud

Can We Stop The Ads? Taxonomy and Characterization of Smartphone Splash Ads and Existing Countermeasures

Study of 108 ad-defense implementations finds only one tool blocked splash-ad navigation across ten popular apps, and it required Accessibility permission.

The paper taxonomizes smartphone splash ads — full-screen ads at app launch that trick users into trigger mechanisms such as moving the phone — and analyzes 108 documented advertising defenses for deployment barriers. Many defenses require device rooting, jailbreaking, runtime code injection, or application modification; others need extra permissions, rule maintenance, compilation, or payment. In evaluating 13 configurations of 11 tools across 10 popular apps, only one prevented ad-triggered navigation across all ten apps, requiring Accessibility permission and leaving ads visible roughly one second before dismissal. Documented harms include delayed emergency response, driver distraction, and degraded accessibility for vision-impaired users.

arXiv cs.CR·Sep 15, 15:24 UTC · 18h agoResearch

New KATARU IoT Malware Packs Linux Privilege Escalation Exploits and Mirai-Style DDoS Attacks

Nozomi Networks identified KATARU, a new Mirai-style IoT botnet delivered via Telnet brute force that uses Linux privilege-escalation exploits and encrypted C2 for DDoS floods.

Nozomi Networks identified KATARU in August after a Telnet password-guessing attack against a honeypot retrieved an ARM payload. The malware attempts exploits for CVE-2026-46300 (Fragnesia), CVE-2026-43284 (DirtyFrag), and CVE-2026-31431 (Copy Fail), plus a cgroup v1 release_agent escape, and persists via systemd services, cron tasks, rc scripts, OpenWrt hooks, and Android boot locations. Its C2 uses X25519 key exchange with ChaCha20-Poly1305 encryption and supports TCP, UDP, ICMP, HTTP, QUIC, and DNS floods, plus SSH brute forcing and command execution; embedded exploit shellcode in the ARM build targeted x86, suggesting untested copied code.

Cyber Security News·Sep 11, 14:17 UTC · 4d agoMalware in the wild 2 sourcesCVE-2026-46300CVE-2026-43284CVE-2026-31431

12 Best Ransomware Protection Solutions Compared (2026): Features & Pricing

GBHackers compares 12 ransomware protection solutions for 2026, recommending layered stacks of EDR prevention, managed detection, containment, and guaranteed recovery.

The editorial comparison argues no single product stops ransomware, recommending a layered strategy across prevention, early detection, blast-radius containment, and clean recovery. CrowdStrike and SentinelOne are named best-in-class EDR, Huntress and Sophos MDR for managed 24/7 coverage, ColorTokens for microsegmentation containment, and Rubrik and Acronis for guaranteed recovery. The guide notes ransomware is now professionalized with double extortion and encryption sprints measured in minutes.

GBHackers·updated 09:52 UTC · 27m ago·first Sep 11, 07:18 UTC · 5d agoIndustry 13 sources1

Notes on gotchas while migrating 35kb preprompts from Opus to self-hosted Ollama

Opinion piece urges migrating 35KB preprompts from Anthropic/OpenAI to self-hosted Ollama, citing session privacy risks and safety filters blocking security research.

The author documents gotchas migrating 35KB preprompts from Claude Opus to self-hosted Ollama, motivated by fears that frontier providers train on user sessions, citing the OpenAI Navier-Stokes controversy. The piece argues inference providers cannot audit their own retention or training pipelines and that only self-hosted hardware offers verifiable privacy. It also criticizes frontier safety filters for refusing vulnerability research tasks and calls for models that support exploitability testing in CI/CD pipelines.

Hacker News · AI·Sep 14, 13:59 UTC · 1d agoAI industryHN 41↑ · 13 comments1

Securing Your Business: The Vital Role of Cyber Insurance | Huntress

Huntress explains cyber insurance coverage types, insurer security requirements, and the shift toward documented evidence of controls.

Huntress outlines first-party and third-party cyber insurance coverage, including business interruption, data recovery, extortion, privacy liability, and regulatory fines. Insurers now commonly require EDR, MFA, security awareness training, patching, tested backups, least-privilege access, and incident response plans. With ransomware accounting for 91% of insurance losses in H1 2025 and average US breach costs at $10.22 million, underwriters increasingly demand evidence packs rather than self-attestation.

Huntress·Sep 1, 16:00 UTC · 14d agoIndustry

Hackers Abuse AutoIt to Inject AsyncRAT Into Microsoft-Signed Windows Process

Attackers use AutoIt and an invoice-themed batch file to inject AsyncRAT into Microsoft-signed charmap.exe for stealthy remote access.

Point Wild Threat Intelligence documented a five-stage campaign starting with 'Right-click to open Invoice Details.bat' that launches hidden PowerShell, drops a renamed AutoIt interpreter and encrypted loader into a random Temp folder, and persists via a Startup-folder batch file. The loader decrypts AsyncRAT only in memory and injects it into the Microsoft-signed charmap.exe (Windows Character Map) process, leaving no payload file on disk. The final payload patches AMSI inside the infected process and includes screen-capture code that prepares images for transfer to a command-and-control server at 158[.]51[.]122[.]136:4944.

Cyber Security News·Sep 14, 07:07 UTC · 2d agoMalware in the wild1

StopAndProtect Turns 2,000 Hacked WordPress Sites Into a Criminal Network

Check Point uncovered StopAndProtect, a cybercrime operation using ~2,000 hacked WordPress sites for ClickFix-driven malware delivery, data theft, surveillance, and ransomware.

Check Point Research identified the StopAndProtect operation in May 2026; it abuses close to 2,000 compromised WordPress sites, many running outdated software, to host malware stages, act as C2, and store stolen data. Infection starts with fake CAPTCHA ClickFix prompts that trick visitors into running a PowerShell command, followed by .NET downloaders deploying ransomware, SMB/USB worm, lockscreen, chat, and credential-stealing components. Rather than always encrypting, operators selectively exfiltrate file lists and specific files; researchers found 700+ stolen-data archives, roughly 31,000 screenshots, and 6,000+ unique victim IP addresses, including WhatsApp activity monitoring.

Security Affairs·Aug 20, 07:20 UTC · 27d agoThreat actor in the wild

Top 10 Best Data Security Posture Management (DSPM) Tools in 2026

A 2026 scorecard ranks DSPM tools with Wiz and Cyera tied first, documenting consolidation via Palo Alto, Rubrik, Proofpoint, and CrowdStrike acquisitions.

The article ranks ten DSPM platforms: Wiz and Cyera tie at 8.7/10, followed by BigID at 8.5 and Securiti at 8.4, scored on discovery breadth, classification accuracy, access context, remediation, and value. It highlights heavy market consolidation, noting Dig Security was acquired by Palo Alto Networks, Laminar by Rubrik, Normalyze by Proofpoint, and Flow Security by CrowdStrike. Buyers are advised to purchase from current owners and confirm post-acquisition integration state.

Cyber Security News·07:29 UTC · 2h agoIndustry

Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic

Multiverse Computing's Hugging Face post argues language models should refuse only the relevant subset of a topic instead of over-refusing whole subjects.

A Hugging Face blog post by Multiverse Computing examines refusal granularity in language models, arguing models should refuse the relevant subset of a topic rather than the entire topic. No full article text was available for additional technical detail.

Hugging Face Blog·Sep 8, 14:23 UTC · 7d agoAI safety & security

The SCREEN Act is a Christian Nationalist Nightmare

404 Media·Aug 4, 17:41 UTC · Aug 4, 2026Policy & legal

Operational Resilience: IT Security Risks with Reduced Staffing | Huntress

Huntress blog advises security teams on managing change, risk, and incident response during reduced-staffing holiday periods.

The article discusses how holiday-period staffing reductions change organizational risk profiles around change management, monitoring, and incident response capability. It argues against blanket change freezes when critical vulnerabilities with high exploitation probability demand patching, and stresses retaining decision-making authority, escalation paths, and recovery knowledge. It concludes by promoting Huntress Managed Response, which lets the Huntress SOC take predefined containment actions on confirmed threats without customer intervention.

Huntress·Sep 15, 14:00 UTC · 20h agoIndustry

The Coding-Agent Trap: When a "Free" LLM Endpoint Is the Adversary, (Mon, Aug 31st)

A SANS honeypot caught a real coding-agent session routed to a rogue "free" LLM endpoint, exposing a Windows user's transcript and tool outputs.

A SANS analyst describes how an internet-exposed inference honeypot was discovered, relabeled with sought-after model names like DeepSeek, and enrolled in infrastructure serving "free" LLM backends. On 2026-08-30 an opencode terminal coding agent sent an 88-message, 224 KB transcript 210 times in 91 seconds via a China Unicom relay, exposing directory listings, tool outputs and read file portions. The analyst frames tool-enabled agents treating model endpoints as trusted control planes as a novel risk — a "rogue model endpoint" that could request tool executions on the user's machine.

SANS Internet Storm Center·Aug 31, 20:00 UTC · 15d agoAI safety & security1

Disruptive cyber activity highlights risk from internet-exposed systems and edge devices

NCSC links disruptive cyber activity to internet-exposed systems and edge devices, urging OT owners to fix avoidable vulnerabilities and improve resilience.

The UK's NCSC issued guidance following disruptive cyber activity that highlights the risk to internet-exposed systems and edge devices. It encourages owners of operational technology to remediate avoidable vulnerabilities and invest in long-term cyber resilience. The notice underscores that exposed edge devices remain a common entry point for attackers against OT environments.

NCSC UK·Aug 27, 12:00 UTC · 19d agoAdvisory in the wild

Top 10 Best Enterprise Browsers in 2026

2026 enterprise browser guide ranks Island first and notes Mammoth Cyber's wind-down plus corrections to standard vendor shortlists.

An editorial guide assesses ten enterprise browser options, ranking category creator Island first for last-mile DLP and BYOD controls, followed by Palo Alto's Talon browser as a Prisma Access/SASE surface and Google Chrome Enterprise Premium for DLP on already-deployed browsers. It corrects common lists, noting SlashNext is browser-adjacent phishing and BEC defense rather than a managed browser, and that Mammoth Cyber has wound down independent operations. Microsoft Edge for Business is positioned as effectively free policy depth for Microsoft 365 estates, with Menlo Security offering an isolation-plus-browser blend.

Cyber Security News·Sep 11, 07:07 UTC · 5d agoIndustry1

Necessary or Sufficient? Evaluating LLM Explanations With Behavioural Evidence

New framework tests whether LLM-cited explanation factors are necessary or sufficient, finding weak correlation across Claude, GPT, and Gemini models.

An arXiv paper introduces black-box intervention tests measuring whether factors LLMs cite in their explanations are necessary or sufficient for their outputs in agent oversight workflows. Across eight models from the Claude, GPT, and Gemini families, Spearman correlations between cited rankings and measured influence ranged from 0.349-0.354 (advisor recommendation) to 0.431-0.580 (prompt monitoring). Uncited factors scored above the lowest cited factor in up to 57.6% of advisor responses, showing cited top-three factors do not reliably identify the most influential inputs.

arXiv cs.AI / cs.LG / cs.CL·Sep 4, 17:37 UTC · 11d agoAI safety & security1

New GPUThor Rowhammer Defeats ECC on NVIDIA RTX A6000 to Gain Host Root Access

University of Toronto researchers present GPUThor, a Rowhammer attack that defeats ECC on NVIDIA RTX A4000-A6000 GDDR6 GPUs and achieves host root access.

GPUThor uses non-uniform hammering to bypass Target Row Refresh and overcome SECDED ECC on NVIDIA Ampere workstation GPUs with GDDR6 memory, inducing 72,000 to 377,552 bit flips per gigabyte across RTX A6000, A5000, A4500, and A4000 cards. Triple-bit silent data corruption enables host privilege escalation to root with the IOMMU enabled, reusing GPUBreach page-table corruption techniques, and double-bit DUEs allow escalation when the IOMMU is disabled during a ~10 ms lazy-service window. The attack cut end-to-end escalation time on the A6000 from 21.9 hours to 1.1 minutes. Reported to NVIDIA, Google, Microsoft, and AWS on April 29, 2026; findings were embargoed until August 25, 2026, and no CVE identifier was assigned.

The Hacker News·Sep 8, 16:03 UTC · 7d agoResearch1

Ncsc Raises Alarms Prompt

The UK NCSC raised alarms about prompt injection risks in LLM-integrated systems, urging organizations deploying AI to review exposure.

The UK National Cyber Security Centre (NCSC) has raised alarms about prompt injection attacks against systems using large language models. The warning highlights how attackers can manipulate model instructions to bypass safeguards, exfiltrate data, or trigger unintended agent actions. Organizations deploying LLM-based features are advised to assess and mitigate their exposure to this technique.

Infosecurity Magazine·Aug 19, 00:00 UTC · 28d agoAI safety & security

Cybersecurity jobs available right now: March 10, 2026

Help Net Security's roundup lists open cybersecurity roles at BioNTech, AIG, ServiceNow and others across Europe, the Middle East and Canada.

A job-board roundup of cybersecurity openings including Associate Director Application Security at BioNTech (Germany), CISO at AIG (Israel), Cloud Security Professional at ServiceNow (Italy), and SOC/GRC, analyst, engineer and data governance roles in the UK, UAE, India, Canada and France. Roles span application security, cloud security, SOC operations, compliance and OT environments. Most listings are marked no longer accepting applications.

Help Net Security·Aug 28, 09:06 UTC · 19d agoIndustry

Inoculation Midtraining with Learned Neologisms

Inoculation Midtraining confines unsafe LLM behavior to a neologism-marked context, reducing misalignment after unsafe post-training but leaking under nearby contextual cues.

The paper introduces Inoculation Midtraining, which teaches a base model during midtraining that unsafe behavior belongs to a context marked by a learned neologism token, then post-trains on unsafe data within that context. Across supervised fine-tuning and RL post-training regimes, the technique reduces misalignment while preserving transfer of benign properties like German or Shakespearean prose. However, it does not outperform standard Inoculation Prompting, is sensitive to training configuration, and produces a leaky boundary that nearby contextual cues can reactivate. The authors conclude it is not yet a load-bearing component of a developer safety framework.

arXiv cs.AI / cs.LG / cs.CL·Sep 14, 17:12 UTC · 1d agoAI safety & security

Proofpoint Strengthens Executive Leadership Team with Appointment of Chief Legal Officer and Chief People Officer

Proofpoint appointed Brian Levey as Chief Legal Officer and Puja Jaspal as Chief People Officer, strengthening its executive leadership team.

Proofpoint announced on September 8, 2026 the appointments of Brian Levey as Chief Legal Officer and Puja Jaspal as Chief People Officer. Levey previously served as Chief Business Affairs & Chief Legal Officer at Upwork and spent 13 years at eBay; Jaspal was Chief People Officer at Fastly with prior senior roles at Cisco, Visa, and Google. The hires support Proofpoint's stated expansion around human and AI-agent security.

Proofpoint Threat Insight·Sep 8, 09:30 UTC · 8d agoIndustry

K-Bench: a clinically calibrated benchmark for evaluating large language models in high-risk mental health conversations

Clinician-calibrated K-Bench evaluates 125 LLM configurations on 200 high-risk mental health vignettes, exposing wide variation in suicide and violence risk handling.

K-Bench is a clinician-calibrated, protected benchmark evaluating 125 model configurations from 33 base models across 14 providers on 200 multi-turn vignettes covering suicide, self-harm, domestic violence, substance misuse and no-risk presentations. A frozen GPT-4o judge achieved 94.2% exact agreement with clinician consensus across 6,751 eligible comparisons from 151 clinician-rated transcripts. Leading models combined supportive conversation with combined-risk scores above 95, while risk exploration varied substantially among weaker configurations; therapeutic prompting helped weaker models and elevated reasoning produced no average improvement. A continuously updated public leaderboard is hosted at k-bench.ai with protected test materials.

arXiv cs.AI / cs.LG / cs.CL·Sep 14, 16:49 UTC · 1d agoAI safety & security

The AI Supply Chain Has a Security Problem, and Much of It Is Sitting on the Open Internet

Researchers counted 36,769 publicly reachable self-hosted AI endpoints, only about 2% behind HTTP authentication, exposing Ollama, vLLM, and Flowise to abuse.

A Mysterium VPN study found 36,769 self-hosted AI endpoints reachable through internet scanning, with only 2.02% returning an HTTP authentication challenge. Open WebUI accounted for 18,529 reachable instances, Ollama for 6,935 fingerprinted hosts, and 5,223 agent-builder and workflow platforms were exposed, often holding API keys, database credentials, and other secrets. The report highlights LLMjacking risk from exposed Ollama APIs, a critical Flowise bug (CVE-2026-40933), leaked n8n tokens, and prior SentinelOne/Censys research finding roughly 175,000 exposed Ollama hosts in 130 countries.

Security Affairs·Sep 11, 17:27 UTC · 4d agoAI safety & securityCVE-2026-409331

Stopping the smart TV from being used against you

Guide describes practical hardening steps to prevent smart TVs from spying on their owners or being used against them.

A tutorial-style post walks through defensive measures to keep a smart TV from collecting user data or being leveraged against its owner. The piece is a consumer IoT privacy and hardening guide rather than a disclosure of a specific vulnerability.

Lobsters · security·Aug 28, 19:32 UTC · 18d agoResearch