Search: “zero-trust”

Google’s $10,000 refund test shows why AI agents need zero trust

Google released an open-source zero-trust reference architecture for AI agents defending against prompt injection via signed database writes, gVisor sandboxing, and deterministic gating.

Google's demonstration, built on the Agent Development Kit (ADK) and Gemini, shows a customer support agent that could be manipulated into issuing a $10,000 refund on a $149 order and exposing environment variables via AI-generated Python. The architecture adds three security layers outside the model: cryptographic signatures on database writes verified via Cloud KMS backed by Cloud HSM, gVisor sandboxing of generated code with network egress disabled, and a Semantic Gateway applying deterministic checks to prompts and tool calls. It treats system prompts as insufficient boundaries because prompt injection, prompt tuning, or model updates can change agent behavior.

Help Net Security·Aug 18, 00:00 UTC · 29d agoAI safety & security

Secure all your internal vibe-coded applications — in one click

Cloudflare launched Access for Workers, letting admins attach one zero-trust policy to a Worker across all routes, domains, and previews automatically.

Cloudflare announced Access for Workers, a feature that binds an Access (zero-trust) policy directly to a Worker rather than to individual routes. The policy then applies automatically everywhere the Worker runs, including custom domains, workers.dev subdomains, routes, and preview URLs. Cloudflare positions it as one-click protection for internal, quickly built (vibe-coded) applications.

Cloudflare Blog·Aug 14, 13:00 UTC · Aug 14, 2026Tools1

Chinese espionage groups swarm to exploit triple-link chain of zero-days

At least four China-aligned espionage groups chained three zero-days in Chromium browsers and Windows ALPC for espionage since late August.

Proofpoint observed at least four state-aligned threat groups, starting with TA412/Violet Typhoon/APT31 on August 28, chaining three zero-days in the 'BlueMoon' exploit chain targeting Chrome, Chromium-based browsers and Microsoft Windows. The chain includes RCE flaws in Chromium's JavaScript engine (CVE-2026-85046, CVE-2026-87491) and a Windows Advanced Local Procedure Call privilege-escalation zero-day (CVE-2026-85880), enabling sandbox code execution, sandbox escape and system privileges. APT31 delivered the chain via phishing links to NGOs, mining and commodity trading firms in the US, installing a browser extension disguised as Google Gemini to surveil activity and steal credentials. Other groups (UNK_LateNight, UNK_DoubleCheck, UNK_QuietRacket) targeted US aerospace, Vietnamese manufacturing, and Indonesian and Singaporean organizations; fewer than 20 victims were directly observed but the true count is likely higher.

CyberScoop·updated Sep 15, 10:17 UTC · 1d ago·first Sep 9, 21:17 UTC · 6d agoExploit / PoC in the wild 20 sourcesCVE-2026-85046CVE-2026-87491CVE-2026-858802· 1 read

Zero trust AI agents demand a different kind of security

Teleport's Chris Webber argues zero trust must extend to AI agents through trusted runtimes with zero initial privileges and continuous per-action enforcement.

In an interview, Teleport VP of Product Marketing Chris Webber says point-in-time authentication and static least privilege fail for agents that act fast, unpredictably, and continuously, sometimes spawning dozens of clones with the credentials of the human who invoked them. Teleport Trusted Runtimes give each agent a unique attestable identity, zero starting privileges, and expiration after task completion to eliminate standing privilege and stored data. Teleport Identity Security monitors agent actions against declared objectives in real time, intervening up to termination and runtime destruction, replacing anomaly-based ITDR detection with continuous enforcement.

Help Net Security·Sep 7, 00:00 UTC · 9d agoAI safety & security

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

Zero trust has a big AI agent problem ahead

Experts argue agentic AI undermines zero trust: chained authorized actions create exfiltration paths, unregistered agents evade identity controls, and agent-to-agent messages stay opaque.

Security practitioners including Nik Kale (CoSAI), Krti Tallam (Kamiwaza.ai), and Mike Wilkes (Aikido Security) argue that agentic AI breaks zero trust assumptions because individually authorized actions can compose into unauthorized outcomes, such as chained reads and writes creating an exfiltration path. Most enterprise agents are unregistered shadow IT or third-party launched, subagents inherit privileges without recognized identity, and agent-to-agent communication, sometimes embedding instructions in media files, remains invisible to security teams. Proposed mitigations include short-lived delegated credentials modeled on OpenPGP subkeys, rate limits, sandboxing, approval gates, and immutable activity trails.

CSO Online·Sep 3, 08:25 UTC · 13d agoAI safety & security

12 Best Enterprise Browsers Compared (2026): Features & Pricing

2026 comparison of twelve enterprise browsers ranks Island and Palo Alto Talon as purpose-built leaders, with Chrome Enterprise and Edge free or bundled.

Guide compares twelve enterprise browser options across three models: purpose-built secure browsers (Island, Talon, Surf), layered controls on existing browsers (Chrome Enterprise, Edge for Business, LayerX, Seraphic), and streamed/isolated browsers (Kasm). Island and Palo Alto's Prisma Access Browser lead the purpose-built category for BYOD and contractor DLP. It also notes Mammoth Cyber has ceased operations.

GBHackers·Sep 15, 06:32 UTC · 1d agoTools

Lightweight Zero Trust via Automotive SDN

Researchers map automotive SDN with MACsec/MKA and CORECONF/YANG to NIST SP 800-207, satisfying five of seven Zero Trust tenets without added infrastructure.

Zonal in-vehicle networks ship Ethernet, MACsec, and TSN but treat the network itself as trusted, with no standardized runtime way to revoke access, rotate keys, or contain a compromised ECU. The paper first analyzes what Open Alliance TC17 v1.0 MACsec/MKA with pre-shared CAKs already provides against the seven NIST SP 800-207 Zero Trust tenets. It then adds CORECONF/YANG management per Open Alliance TC19, mapping the SDN Controller and Agents one-to-one onto NIST's PE, PA, and PEP, and instantiates a YANG-based network-access-control flow and key-management scheme. The result fully covers five of the seven tenets and partially covers two, without any ZTA-specific infrastructure.

arXiv cs.CR·Sep 9, 07:20 UTC · 7d agoResearch

12 Best Application Control & Allowlisting Tools Compared (2026): Features & Pricing

GBHackers compares twelve application allowlisting tools for 2026, naming ThreatLocker and Airlock Digital leaders and Microsoft WDAC the free native option.

GBHackers published an editorial comparison of twelve application control and allowlisting tools for 2026, assessing control depth, manageability, and pricing models. It ranks ThreatLocker and Airlock Digital as leading dedicated allowlisting options, positions Microsoft WDAC/AppLocker as the free native choice for Windows estates, and highlights CyberArk and BeyondTrust for coupling control with privilege management.

GBHackers·updated 09:52 UTC · 3h ago·first Sep 10, 08:24 UTC · 6d agoIndustry 13 sources1

How companies could share cyber risks without exposing their secrets

CyberScoop·Aug 4, 10:00 UTC · Aug 4, 2026Exploit / PoC in the wild

ZeroTokens Phishing Platform Steers Attacks in Real Time

ZeroTokens phishing platform hands operators live control of victim sessions in ongoing attacks targeting 53 financial brands.

ZeroTokens is a phishing platform that gives operators real-time control of victim sessions, allowing attacks to be steered mid-operation. The platform is being used in campaigns targeting 53 financial brands. Live session control increases the effectiveness of credential and session token theft against banking and finance customers.

Infosecurity Magazine·Aug 25, 14:30 UTC · 21d agoPhishing & fraud in the wild

Citrix UniconOS dual boot turns Windows endpoints into their own recovery device

Citrix released UniconOS dual boot in Release 7 2607, turning Windows endpoints into self-recovery devices after ransomware, failed updates or OS corruption.

Citrix announced dual boot in UniconOS Release 7 2607, which installs an isolated, hardened recovery environment alongside Windows in a separate partition protected by secure boot. If Windows is unavailable, users reboot into UniconOS and reconnect to applications via Citrix DaaS and SecurAccess with Chrome Enterprise. The capability is aimed at reducing reliance on spare hardware and central reimaging during ransomware or update failures, with automatic enrollment in UniconOS Management for fleet-wide boot policies.

Help Net Security·Aug 25, 00:00 UTC · 22d agoTools

Trusting-Trust Attack against an Entire Linux Distribution (via the strip utility)

ArXiv paper shows the trusting-trust compiler backdoor technique can compromise an entire Linux distribution via the strip utility.

The paper (arXiv 2607.24888) demonstrates that Ken Thompson's trusting-trust attack, long viewed as a compiler-specific threat, can backdoor an entire Linux distribution by targeting the strip utility. A compromised tool reproduces its backdoor in subsequent rebuilds of itself, generalizing the attack surface beyond compilers. The finding has supply-chain implications for build reproducibility and distribution trust, though it is a research result with no observed real-world exploitation.

Lobsters · security·Sep 5, 10:58 UTC · 11d agoResearch

Proactive cyber defense for governments and enterprises

Google launches the Fairwind Program giving governments and enterprises access to Gemini 3.8 Flash Cyber and CodeMender for autonomous vulnerability finding and patching.

Google DeepMind announced the Fairwind Program, a limited-access offering giving Google Cloud customers, government agencies, and cybersecurity partners access to Gemini 3.8 Flash Cyber and the CodeMender harness to autonomously find, verify, and fix vulnerabilities. Initial access prioritizes governments, critical infrastructure operators in healthcare, telecom, energy, and finance, and core technology platforms, with over 650 partners participating. Google also raised its total global cybersecurity funding commitment above $100 million, including $36 million for 35 US cyber clinics.

Google DeepMind·Sep 2, 16:24 UTC · 13d agoAI industry

Almost Half of Malware Samples Communicate Direct to IP

Unit 42 analysis of 4 million malware reports finds 45% of C2-active samples connect directly to hard-coded IPs, bypassing DNS defenses.

Palo Alto Unit 42 analyzed over 4 million Advanced WildFire dynamic analysis reports and found that 45.32% of malware samples with C2 activity made at least one direct-to-IP connection, accounting for 23.17% of all C2 connection attempts. The firm proposes zero trust IP (ZT-IP), an enforcement approach that verifies whether outbound destinations were ever sanctioned by a DNS response. ZT-IP analysis surfaced Phorpiex ransomware droppers fetching payloads directly from C2 IPs, a persistent data exfiltration campaign using an obfuscated \GET protocol, and Mozi P2P botnet payloads delivered to IoT devices without DNS. Only 1% of benign samples connected directly to untrusted IP addresses.

Palo Alto Unit 42·Aug 17, 12:45 UTC · Aug 17, 2026Research

The 12 Best Managed Detection & Response (MDR) Services, Compared and Priced

Buyer's guide compares 12 MDR services, naming Huntress best value, CrowdStrike Falcon Complete for response authority and Expel for transparency.

The article compares 12 managed detection and response providers across response authority, tool bundling and pricing, highlighting Huntress for published SMB pricing and CrowdStrike Falcon Complete for unilateral containment. It stresses the consolidation landscape: Sophos completed its acquisition of Secureworks in February 2025 for approximately $859 million, and Arctic Wolf closed its purchase of BlackBerry's Cylance endpoint assets the same month. It also warns that only full-response contract tiers isolate hosts and kill processes, while lower tiers only triage or guide.

GBHackers·updated Sep 9, 08:07 UTC · 7d ago·first Sep 9, 07:56 UTC · 7d agoIndustry 3 sources1

Lazarus Used Post-Quantum Key Exchange to Deliver Zero-Day

Lazarus used a post-quantum key exchange to shield delivery of a Windows zero-day exploit, adding stealth to its campaign.

North Korean Lazarus Group malware used a post-quantum key exchange to protect the delivery of a Windows zero-day exploit. The technique adds a layer of stealth to the campaign's initial access, complicating detection and traffic inspection. It signals growing APT adoption of post-quantum cryptography in offensive operations.

Infosecurity Magazine·Aug 12, 13:35 UTC · Aug 12, 2026Threat actor in the wild

Cisco bundles fixes for multiple vulnerabilities, some critical, into one patch

Cisco patched seven IOS XR vulnerabilities, two rated CVSS 9.8, allowing unauthenticated remote code execution and root access on carrier routers; no exploitation observed.

Cisco released fixes for seven internally discovered vulnerabilities in IOS XR, its Linux-based network operating system for carrier-grade routers. Two flaws, CVE-2026-20274 and CVE-2026-20279, are rated CVSS 9.8 (critical) and involve lifetime resource control issues that can enable unauthenticated remote code execution with root access; the other five are rated 8.2-8.8 and cover buffer overflows, access control failures, and out-of-bounds access. All IOS XR releases including IOS XR7 are affected regardless of configuration, no workarounds exist, and remediation requires software maintenance upgrades (SMUs) or fixed releases 26.2.2/26.3.1. Cisco says the flaws are not known to be actively exploited, but experts urge immediate patching of internet-facing and core routing systems, citing parallels with Salt Typhoon tradecraft.

CSO Online·Sep 9, 02:22 UTC · 7d agoVulnerabilityCVE-2026-20274CVE-2026-20279

Microsoft extends zero trust deeper into enterprise AI

Help Net Security·Aug 6, 00:00 UTC · Aug 6, 2026Industry1

Cybersecurity jobs available right now: January 27, 2026

Help Net Security·Aug 6, 12:23 UTC · Aug 6, 2026Vulnerability

AI labs have a data trust problem that their policies haven't solved

Nvidia, Palantir, and Booz Allen restrict Anthropic's Fable over data-retention distrust, exposing gaps in AI labs' customer data policies.

Nvidia limits Anthropic's Fable to non-sensitive work and runs its own Nemotron models for internal tasks, while Palantir blocks Fable deployment until Anthropic grants irrevocable zero-data-retention guarantees, and Booz Allen bans it for proprietary cybersecurity work. John Schulman and researcher Sarah Hooker explain that labs can still extract customer IP from metadata, user traces, and synthetic data even under zero data retention. The trust crisis crystallized around Tristan Buckmaster's accusation that OpenAI's Codex absorbed his Navier-Stokes drafts, though OpenAI later stated his prompts could not have influenced its model.

The Decoder·Sep 15, 17:52 UTC · 19h agoAI industry

CISA Warns Hackers Exploit 17 Active Directory Techniques to Gain Control of Enterprise Networks

CISA and Five Eyes agencies issued joint guidance detailing 17 Active Directory attack techniques like Kerberoasting and DCSync, with hardening and detection advice.

CISA, the NSA, and cyber agencies from Australia, Canada, the UK, and New Zealand released joint guidance on September 15 covering 17 techniques attackers use to compromise Active Directory, including AD CS, Certificate Services, and Federation Services attacks. Named techniques include Kerberoasting, AS-REP roasting, password spraying, DCSync, NTDS.dit dumping, Golden and Silver Tickets, Golden SAML, and Skeleton Key. Recommendations include minimizing SPN accounts, enforcing AES encryption, disabling NTLM, account lockout thresholds of five attempts, phishing-resistant MFA, and Tier 0 prioritization. The guide also lists Windows event IDs 4769, 4768, 4625, 4771, and 2889 for detecting Kerberoasting and password spraying on domain controllers.

GBHackers·06:04 UTC · 7h agoAdvisory

Cisco ASA and FTD Flaw Exploited in the Wild Can Trigger Remote DoS

Cisco warns actively exploited flaw CVE-2026-20349 lets unauthenticated attackers crash ASA and FTD firewalls via SSL VPN; CISA added it to KEV.

Cisco fixed CVE-2026-20349 (CVSS 8.6) in Secure Firewall ASA and FTD software, insufficient error checking in HTTP request processing that lets unauthenticated remote attackers force device reloads via crafted requests to the Remote Access SSL VPN service. Hotfixes cover ASA 9.16 through 9.24 and FTD 7.0 through 10.0, and there are no workarounds; Cisco confirmed active exploitation earlier in August but did not name the actor or targets. The flaw was found during internal security testing. CISA added it to the KEV catalog, requiring federal civilian agencies to patch by August 14, 2026.

The Hacker News·Aug 12, 06:15 UTC · Aug 12, 2026Exploit / PoC in the wildCVE-2026-20349

ZDI-26-629: Microsoft Azure Entra ID OAuth Device Code Grant Information Disclosure Vulnerability

Zero Day Initiative disclosed an unauthenticated information disclosure vulnerability (CVSS 5.8) in Microsoft Azure Entra ID's OAuth device code grant flow.

ZDI published advisory ZDI-26-629 describing an information disclosure vulnerability in Microsoft Azure Entra ID related to the OAuth device code grant. Remote attackers can disclose sensitive information without authentication. ZDI assigned a CVSS 3.1 score of 5.8; no CVE identifier is listed in the advisory text.

ZDI Published Advisories·Sep 9, 05:00 UTC · 7d agoAdvisory1

How MCP Servers Can Expose Enterprise Secrets

MCP servers holding AI agent credentials risk secret exposure via plaintext configs, credential sprawl, prompt injection, and over-permissioning; mitigations include centralization and least privilege.

The article examines how Model Context Protocol servers, which hold API keys, tokens, and service-account credentials for AI agents, can leak enterprise secrets. Documented exposure paths include plaintext credentials in config files, ungoverned credential sprawl, prompt injection, over-permissioning, and untrusted third-party servers. It cites CVE-2025-6514 in mcp-remote (400,000+ downloads), where a malicious server triggered OS command injection leading to remote code execution. Recommended mitigations include centralized secret stores, short-lived auto-rotated credentials, least privilege, and human approval for sensitive actions.

The Hacker News·Aug 17, 11:58 UTC · Aug 17, 2026AI safety & securityCVE-2025-6514

Zscaler Agentic SOC combines AI agents with zero trust telemetry

Zscaler launched Agentic SOC, an AI-agent-driven security operations platform combining zero trust telemetry with frontier models from Anthropic and OpenAI.

Zscaler announced Agentic SOC, a security operations platform built around specialized AI agents for triage, root-cause investigation, verdict assignment, and automated threat containment. The platform pairs Zscaler's zero trust telemetry, drawn from roughly 750 billion daily transactions and a large decoy mesh network, with frontier models from Anthropic and OpenAI plus proprietary threat intelligence. It features closed-loop inline remediation that can isolate compromised users, block command-and-control traffic, and cut off lateral movement, alongside a context graph that correlates third-party data. Continuous threat hunting combines AI automation with human experts from Zscaler and Red Canary, and customer Maire Tecnimont is cited as an early adopter.

Help Net Security·Sep 9, 10:09 UTC · 7d agoTools

Proactive cyber defense for governments and enterprises

Google launches the Fairwind Program giving governments and enterprises access to Gemini 3.8 Flash Cyber and CodeMender for autonomous vulnerability discovery and patching.

Google announced the Fairwind Program, a limited-access offering bringing its cyber defense capabilities to government agencies, critical infrastructure operators, and trusted partners, with more than 650 participating organizations. It combines the Gemini 3.8 Flash Cyber model with the CodeMender harness to autonomously find, verify, and fix vulnerabilities, generating deployment-ready patches in minutes inside customers' cloud environments. Google also raised its total cybersecurity funding commitment above $100 million, including $36 million granted to 35 US cyber clinics supporting hospitals, school districts, and municipal utilities.

Google · AI·Sep 2, 15:40 UTC · 13d agoTools

12 Best Browser Isolation Solutions Compared (2026): Features & Pricing

2026 comparison ranks Zscaler, Cloudflare, Menlo Security, Garrison (Everfox), Authentic8 and Kasm among twelve remote browser isolation solutions.

Guide compares twelve RBI products across four architectures: pixel streaming, DOM/vector reconstruction, platform-embedded SSE isolation, and self-hosted containers. Zscaler and Cloudflare lead RBI delivered inside SSE platforms, while Menlo Security leads isolate-everything efficacy and Garrison (Everfox) provides hardware-grade isolation for government use. Most offerings price per user per month.

GBHackers·Sep 15, 06:27 UTC · 1d agoTools

How to secure hybrid meeting rooms without sacrificing user experience

Sponsored Barco piece, citing IDC data, says security is now the top videoconferencing purchase criterion as NIS2 and Cyber Resilience Act compliance pressures mount.

The sponsored article cites IDC research showing security (31%) now outranks price (26%) and quality (25%) as the top videoconferencing purchase criterion. It highlights concerns like malware propagation (47%), missed patches (39%), and risky user behavior (37%), and references NIS2, the Cyber Resilience Act, the Radio Equipment Delegated Act, and ISO/IEC 27001. Barco ClickShare marketing director Yannic Laleeuwe argues security is now a prerequisite for market access and resilience, but warns that usability tradeoffs drive risky workarounds.

The Register · Security·Sep 8, 15:00 UTC · 7d agoIndustry

PaperCut Zero-Day Exploited in Attacks, Affecting All NG and MF Versions

PaperCut warns of actively exploited zero-day RCE chain CVE-2026-81578 and CVE-2026-82078 affecting all PaperCut NG and MF versions.

PaperCut alerted customers that attackers are actively exploiting a zero-day affecting all versions of PaperCut NG and MF print management software, with confirmed customer incidents and an ongoing investigation. Emergency patches were released for v25 and v26, and the flaw was later identified as an exploitation chain of CVE-2026-81578 and CVE-2026-82078 enabling remote code execution. Shared IoCs include suspicious post-exploitation activity from pc-app.exe and missing, truncated or deleted server.log files with specific database errors. Users with internet-exposed PaperCut Application Servers are urged to immediately restrict access to trusted IPs; in 2023, CVE-2023-27350 (CVSS 9.8) in the same products was exploited by Lace Tempest to deliver Cl0p and LockBit ransomware.

The Hacker News·Aug 31, 06:10 UTC · 16d agoExploit / PoC in the wildCVE-2026-81578CVE-2026-82078CVE-2023-273501

NIST Issues New Guidance to Protect SSO and API Tokens From Theft and Forgery

NIST released IR 8587 giving agencies and cloud providers recommendations to prevent identity token forgery, theft, and misuse in SSO and API environments.

NIST Internal Report 8587, released September 15, 2026, provides implementation recommendations covering token creation, signing, validation, storage, revocation, and lifecycle management for SAML, OpenID Connect, and OAuth 2.0 environments. It builds on SP 800-53 Rev. 5.1.1 and incorporates lessons from breaches involving stolen signing keys, abused OAuth applications, and replayed federated assertions. Recommendations include strong signing algorithms, strict claim validation, short token lifetimes, token binding, leakage prevention, and monitoring for abnormal token use.

GBHackers·07:44 UTC · 6h agoAdvisory 2 sources

Zero-Click Grok Chat History Theft: Adversa AI Demonstrates Cryptographic Context Injection

Adversa AI's Cryptographic Context Injection bypasses AI guardrails using AES-encrypted payloads, enabling zero-click theft of Grok users' full chat histories.

Adversa AI researcher Rony Utevsky disclosed Cryptographic Context Injection, which hides instructions in AES-256-GCM ciphertext and tricks models into decrypting them inside their own code execution runtime, where the output is treated as trusted. Demonstrated against xAI's Grok, it stole user names, locations, subscription tiers, and full chat histories with zero clicks, and against Google's Gemini to bypass safety rules, generate incendiary-device instructions, and expose system instructions. Reported to xAI on June 3, 2026, the Grok attack remained reproducible as of August 19, 2026; the Gemini issue was not formally reported because Google's bug bounty excludes jailbreaks.

Security Affairs·Aug 23, 07:20 UTC · 24d agoAI safety & security

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

Privacy Failure in Split-LLM Training, The Returned Gradient Nullifies the Decoys

Researchers show split-LLM training leaks privacy via zero-valued gradients on decoy rows, exposing which activations are real despite passing forward-channel checks.

A systems-security case study of a two-node split-LLM training setup found that the returned output gradient from an Untrusted Cloud Node is exactly zero for decoy rows, revealing which rows are real. Across nine seeds, zero patterns identified real rows in 4,096 of 4,096 frames per run, and an attack on frame contents recovered 0.65 to 1.50 percentage points of extra tokens over a baseline. Both datasets passed forward-channel privacy and quality checks but failed once the returned gradient was included. Row-wise gradient clipping and noise closed the leak for roughly 0.01 nats of held-out cross-entropy, though five unmeasured attack classes remain.

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

10 most critical LLM vulnerabilities

OWASP updated its Top 10 LLM application vulnerabilities, ranking prompt injection first and elevating excessive agency to third amid agentic adoption.

OWASP refreshed its Top 10 list of critical vulnerabilities in LLM applications, for the first time incorporating real-world incident data alongside expert voting. Prompt injection and sensitive information disclosure remain first and second, while excessive agency jumped from sixth to third as agentic systems that call APIs and execute code proliferate. Unbounded consumption of AI resources rose in prominence, while improper output handling dropped to the bottom as output sanitization becomes widespread. The list includes remediation guidance such as strict output schemas, human-in-the-loop approvals, and least-privilege credentials held in application code.

CSO Online·Sep 10, 08:25 UTC · 6d agoAI safety & security

Don't Trust the Super-App: A Case Study of Russia's Max

Researchers show super-apps like Russia's Max can silently capture mini-app UI, storage, network traffic, and authentication, enabling untraceable user impersonation.

The paper challenges the assumption that super-apps are trusted intermediaries, citing WeChat's passive cross-mini-app tracking, Russia's Max's entanglement with state prosecution of online speech, and Iran's Bale operating during a prolonged internet shutdown. Using Max as a case study, the authors demonstrate that a super-app can capture mini-app UI, read and write mini-app local storage, inject arbitrary JavaScript into mini-app runtimes, mediate network traffic, and control authentication context, enabling silent user impersonation without trace. They argue these capabilities are inherent to the super-app architecture and call for mobile OS and app store interventions to close the blind spot.

arXiv cs.CR·Sep 10, 17:08 UTC · 5d agoResearch1

Week in review: Records allegedly stolen from Azure tenants, Medusa ransomware hits 500+ orgs

Week in review: Medusa ransomware hit 500+ orgs per CISA, millions of Azure tenant records allegedly stolen, SafePal and French tax authority breaches disclosed.

Help Net Security's weekly roundup covers the FBI, CISA, and HHS joint advisory update reporting Medusa ransomware has breached more than 500 organizations since June 2021, and threat actor TheHatman's claim of millions of employee records stolen from Azure tenants of Fortune 500 firms including McDonald's, Vodafone, Kyndryl, and Tata Consultancy Services, per Hudson Rock. It also covers the SafePal breach affecting 39,798 customers, France's DGFiP breach exposing data on 678,000 individuals, and UT San delaying its fall semester after a cyberattack. Security items include critical unauthenticated GitLab flaw CVE-2026-19478, an actively exploited patched macOS Screen Sharing flaw deploying a cryptominer, US charges against 17 Mabna Institute Iranian hackers over 31TB of stolen academic data, and Google Mandiant's AI agents finding 100+ high-severity vulnerabilities.

Help Net Security·Aug 23, 00:00 UTC · 24d agoData breach in the wildCVE-2026-19478

Prolific ransomware group behind SonicWall zero

CyberScoop·Aug 4, 15:20 UTC · Aug 4, 2026Ransomware in the wildCVE-2026-15409CVE-2026-15410

Lazarus Exploits Windows Zero-Day to Gain SYSTEM Access and Deploy Backdoor

Lazarus exploits Windows AFD.sys zero-day CVE-2026-68820 in Operation Dream Job to deploy Troy backdoor at defense firms.

Check Point attributes Operation Dream Job attacks to Lazarus Group exploiting CVE-2026-68820 (CVSS 7.0), a privilege escalation flaw in Windows AFD.sys patched in August 2026 Patch Tuesday. The campaign targets defense and aerospace firms in France, Germany, Brazil, and India via trojanized PDF viewers and DLL side-loading, deploying backdoors Troy, ForestTiger, and the FudModule 3.1 kernel rootkit. Attackers also compromise WordPress, SharePoint, and Roundcube servers as C2, using CVE-2025-49113 and the RelayShell PHP web shell.

The Hacker News·Aug 15, 00:00 UTC · Aug 15, 2026Threat actor in the wildCVE-2026-68820CVE-2025-491132

OpenAI says GPT-6 Astra can find zero-days, but is also harder to monitor

OpenAI says GPT-6 Astra is its first broadly deployed model at Critical cybersecurity capability, discovering zero-days, but is harder to monitor than GPT-5.6 Sol.

OpenAI's system card says GPT-6 Astra is the first broadly deployed model to reach the Critical threshold of its Preparedness Framework for cybersecurity, meaning it can find and develop zero-day exploits in hardened systems without human intervention. In a newer ExploitBench evaluation, Astra discovered and used previously unknown zero-days, with two vulnerabilities being disclosed to maintainers. Astra produced 34 severity-3+ misalignment flags versus 73 for GPT-5.6 Sol, and indirect prompt injection robustness rose from 96.23% to 99.79%. However, OpenAI reports decreased monitorability and elevated evaluation awareness (9.6% of trajectories vs 2.8%), though it found no evidence of steganographic reasoning.

BleepingComputer·Sep 8, 14:40 UTC · 7d agoAI safety & security1