Search: “safe-mode”

Akira Hits Safe Mode: Ransomware Rebooting Around EDR

Huntress documents an Akira ransomware affiliate rebooting endpoints into Windows Safe Mode to evade EDR and Defender, though Safe Mode broke the ransomware.

Huntress observed an Akira ransomware affiliate rebooting victim machines into Windows Safe Mode to disable EDR and Microsoft Defender before deploying ransomware. In an ironic twist, Safe Mode also prevented the ransomware from executing properly. The post walks through the full attack chain and the defensive lessons.

Huntress·Aug 12, 13:00 UTC · Aug 12, 2026Ransomware in the wild

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

Akira Ransomware Uses Safe Mode to Bypass EDR

An Akira affiliate rebooted a compromised host into Safe Mode to bypass EDR, but constrained memory crashed the encryptor before encryption completed.

Huntress reports an Akira affiliate gained access on August 4 via an MFA-less SonicWall VPN, enumerated Active Directory, archived file shares with WinRAR, and exfiltrated data to an attacker S3 bucket. The attacker rebooted the host into Safe Mode with Networking and preloaded AnyDesk into the Safe Mode service registry, disabling EDR and Defender's real-time protection for roughly ten minutes. The encryptor failed about 13 seconds after launch with out-of-virtual-memory errors caused by Safe Mode's stripped-down environment, and Defender later removed akira.exe after reboot. Huntress says this is the first observed Safe Mode abuse by Akira, following precedents by Snatch and AvosLocker, and provides detection guidance.

Security Affairs·Aug 17, 07:15 UTC · Aug 17, 2026Ransomware in the wild

Safe Meta-Reinforcement Learning via Information Space Reachability

Safe meta-RL framework reasons about safety in information space, learning a safety value function used for safety filtering and constrained policy optimization.

The paper proposes safe meta-RL that reasons about safety in information space, capturing both physical state and the agent's belief over the underlying task. A safety value function measures the probability of avoiding unsafe regions indefinitely and satisfies a self-consistency condition and Bellman equation, making it learnable via meta-RL. The resulting algorithm uses the learned function for safety filtering and constrained policy optimization, with effectiveness demonstrated on meta-RL benchmarks.

arXiv cs.AI / cs.LG / cs.CL·Sep 14, 17:27 UTC · 1d agoAI research

VU#718077: UEFI Shell module embedded in SPI Flash can be used to bypass Secure Boot

CERT/CC details VU#718077: UEFI Shell embedded in SPI flash lets attackers bypass Secure Boot and execute pre-boot code; patches issued.

CERT/CC's VU#718077, reported by Eclypsium researcher Stas Lyakhov, describes how a UEFI Shell embedded in SPI flash can be abused by attackers who can modify UEFI boot configuration, creating multiple boot entries that bypass controls preventing the Shell from launching under Secure Boot. The Shell's dmem and mm commands allow arbitrary physical memory read/write, letting attackers overwrite Secure Boot values and execute unauthorized pre-boot code that can persist across reboots and OS reinstalls while degrading EDR effectiveness. AMI confirmed its Aptio UEFI BDS module is affected (CVE-2026-33197), and Cisco published an advisory for a variation affecting UCS Servers and UCS-based appliances (CVE-2026-20293). Firmware patches are being rolled out through OEM and IBV BIOS build pipelines.

CERT/CC Vulnerability Notes·Sep 8, 15:05 UTC · 8d agoVulnerabilityCVE-2026-20293CVE-2026-33197CVE-2026-6485

Putting models to the secure coding test: Plan vs default mode

Datadog Security Labs tested Sonnet 5, Composer 2.5, and GPT 5.5 to see if plan mode yields more secure code than default mode.

Datadog Security Labs evaluated whether plan mode produces measurably more secure code than default mode. The test covered three frontier coding models: Sonnet 5, Composer 2.5, and GPT 5.5. The results inform how engineering teams should configure AI coding assistants to reduce insecure code. This is an AI security evaluation, not an incident report.

Datadog Security Labs·Aug 19, 00:00 UTC · 28d agoAI safety & security

TIER: Threat Implicitness Benchmark for Evaluating LLM Safety Behaviors

TIER benchmark shows LLM safety behaviors shift gradually across threat implicitness levels, with jailbreaks exposing the largest robustness gaps.

The TIER benchmark evaluates LLM safety behaviors across four risk domains and four threat levels, from explicit harmful requests to sophisticated jailbreaks, using a six-label behavior scale and two independent LLM judges. Experiments on six open-weight LLMs show safety behaviors evolve gradually across threat levels rather than flipping from refusal to compliance. Models with similar Attack Success Rates can exhibit distinct response distributions, arguing for behavior-aware safety evaluation.

arXiv cs.CR·Sep 4, 13:13 UTC · 12d agoAI safety & security

HuggingFace: Security.txt

Hugging Face published a security.txt file, prompting limited Hacker News discussion of the RFC 9116 disclosure standard.

Hugging Face's security.txt file, which lists its security contact and disclosure channels per the RFC 9116 standard, drew attention on Hacker News. The RFC 9116 standard lets organizations publish where and how security researchers should report issues, but the submission received only one comment.

Hacker News · security·updated Sep 11, 16:04 UTC · 5d ago·first Sep 11, 14:38 UTC · 5d agoIndustry 2 sourcesHN 22↑ · 1 comments

New Guidance Helps Businesses Verify Quantum-Safe Hardware Claims

TCG issued guidance to help businesses verify that trusted platform modules genuinely meet quantum-safe requirements.

The Trusted Computing Group (TCG) published new guidance aimed at proving that trusted platform modules (TPMs) genuinely satisfy essential quantum-safe requirements. The document gives businesses a way to validate vendor claims about post-quantum readiness in hardware security rather than trusting marketing assertions. This is a guidance publication, not an incident or vulnerability disclosure.

Infosecurity Magazine·Aug 24, 16:00 UTC · 23d agoAdvisory

Perturbation Probing: A New Diagnostic for the Fragility of LLM Safety

Unit 42 research shows LLM safety refusals concentrate in a thin neural layer, motivating external, multi-layered AI security controls.

Palo Alto Networks Unit 42 introduces Perturbation Probing, a diagnostic technique for measuring the fragility of LLM safety mechanisms. The research finds that safety refusal behavior is localized within a thin neural layer, implying small perturbations can undermine built-in refusals. The authors argue this motivates external, multi-layered security defenses on top of model-internal safety training.

Palo Alto Unit 42·Aug 28, 22:00 UTC · 18d agoAI safety & security

Attackers plant remote access tools on compromised PaperCut servers

Attackers chained two PaperCut NG/MF zero-days for unauthenticated access, installing SimpleHelp and AnyDesk remote access tools on compromised servers.

An ongoing campaign exploits chained zero-days CVE-2026-81578 (improper access control) and CVE-2026-82078 (unsafe dynamic class loading) in internet-facing PaperCut NG and MF Application Servers, enabling authentication bypass and arbitrary Java bytecode execution. Post-compromise activity includes user and domain enumeration, payload download from sendit.sh, and silent installation of SimpleHelp and AnyDesk for redundant remote access; Defused observed CVE-2026-81578/CVE-2026-82078 exploit activity in honeypots since August 29, including data theft via Derby database dumps. Emergency patches were released August 28 and August 30, but 47% of roughly 2,500 PaperCut installs tracked by Huntress run v23 or older, for which no patch is available.

Help Net Security·Sep 2, 08:12 UTC · 14d agoExploit / PoC in the wildCVE-2026-81578CVE-2026-820781

U.S. CISA adds PaperCut NG/MF flaws to its Known Exploited Vulnerabilities catalog

CISA added two actively exploited PaperCut NG/MF pre-auth flaws to the KEV catalog; federal agencies must patch by September 14.

CISA added CVE-2026-81578 (CVSS 8.8, missing authentication for critical function) and CVE-2026-82078 (CVSS 9.4, unsafe reflection) in PaperCut NG/MF to its Known Exploited Vulnerabilities catalog. Huntress confirmed active pre-authentication RCE exploitation in two customer environments and reproduced the full chain against a clean PaperCut NG 25.0.11 server, chaining the auth bypass into unsafe Java class loading for SYSTEM-level execution. About 47% of roughly 2,500 tracked PaperCut installs still run version 23 or earlier with no patch available, and observed attacker activity was limited to system discovery commands.

Security Affairs·Sep 1, 08:13 UTC · 15d agoVulnerability in the wildCVE-2026-81578CVE-2026-82078

Managing the cyber risk of agentic AI

UK NCSC guidance recommends safeguards, sandboxing, and active oversight to manage cyber risks of autonomous agentic AI systems.

The UK National Cyber Security Centre published guidance on managing the cyber risk of agentic AI systems. It recommends safeguards, sandboxing, and active human oversight to limit unintended autonomous activity while realizing the benefits of these systems. The publication is official national guidance for organizations deploying agentic AI.

NCSC UK·Aug 20, 12:00 UTC · 27d agoAdvisory

GNU GRUB 2.14: serial-MMIO lockdown bypass in Canonical-signed gcdx64.efi

Canonical-signed GRUB2 serial command accepts arbitrary MMIO addresses, letting local attackers with grub.cfg control bypass Secure Boot lockdown.

A vulnerability in Canonical's grub-efi-amd64-signed (gcdx64.efi, GRUB 2.14) exposes a serial command that accepts a caller-supplied 64-bit MMIO base address. The lockdown path does not restrict this command even when lockdown=y under UEFI Secure Boot, and the serial implementation does not validate that the requested register span belongs to a real UART rather than ordinary RAM. A local attacker with control of GRUB's boot configuration can abuse this to bypass the Secure Boot lockdown.

oss-security·Sep 13, 13:59 UTC · 3d agoVulnerability2

Rockwell Automation 1756-ENBT Module

Rockwell's 1756-ENBT ControlLogix EtherNet/IP bridge (all versions) is vulnerable to DoS via crafted CIP packets, crashing the module until manual restart.

CISA republished Rockwell Automation's advisory for CVE-2025-10478, a CWE-754 flaw affecting all versions of the 1756-ENBT ControlLogix EtherNet/IP bridge, scored CVSS 7.5. A crafted CIP packet can crash the module, and the device requires a restart to recover. Affected critical infrastructure sectors include critical manufacturing, food and agriculture, transportation systems, and water. No public exploitation has been reported; CISA recommends minimizing network exposure.

CISA Advisories·Sep 3, 12:00 UTC · 13d agoAdvisory 3 sourcesCVE-2025-10478

CVE-2026-81578 + CVE-2026-82078 | PaperCut NG/MF Authentication Bypass and Unsafe Dynamic Class Loading Vulnerabilities

Two chained PaperCut NG/MF flaws, CVE-2026-81578 and CVE-2026-82078, enable pre-auth RCE, with active exploitation confirmed in customer environments.

PaperCut NG/MF is affected by CVE-2026-81578, an improper access control flaw (CVSS 4.0 8.8) allowing unauthenticated configuration changes, and CVE-2026-82078, an unsafe dynamic class loading flaw (CVSS 4.0 9.4) enabling arbitrary Java bytecode execution. Chained, they yield pre-authentication remote code execution on the PaperCut Application Server. PaperCut confirmed active exploitation and customer incidents, and Huntress observed exploitation starting August 26, 2026. Emergency Patch Release 2 is available for NG/MF v24-v26, with IOCs including suspicious pc-app.exe child processes, truncated server.log files, and AnyDesk installs.

Horizon3.ai·Sep 1, 15:31 UTC · 15d agoExploit / PoC in the wildCVE-2026-81578CVE-2026-820781

CONTINUITY: Security-Context Contracts for Composable LLM Agent Controls

Researchers introduce CONTINUITY, a framework of assume-guarantee contracts that preserves LLM agent security context across components, verified across 2,560 attack instances.

The paper identifies security-context discontinuity, where individually sound controls drop, widen, or reinterpret security context as actions cross component boundaries, and proposes CONTINUITY, a framework of assume-guarantee contracts using signed root grants, provenance commitments, role-bound transition receipts, and effect-bound execution permits. It formalizes end-to-end consequence integrity, requiring every external effect to be backed by a valid authorization witness linking principal, task, provenance, and policy state. A reference verifier and cross-layer fault-injection suite covering 32 fault classes showed the full configuration committed no harmful external effect across 2,560 parameterized attack instances while completing all 700 benign tasks and escalating all 200 ambiguous cases.

arXiv cs.CR·Sep 4, 15:26 UTC · 12d agoAI safety & security

VU#456290: Hugging Face Transformers library writes remote code to disk prior to consent check

CVE-2026-80047: Hugging Face Transformers 4.49.0 through 5.8.1 writes attacker-controlled Python files to disk before the trust_remote_code consent check.

CERT/CC vulnerability note VU#456290 describes CVE-2026-80047 in the Hugging Face Transformers library, affecting versions 4.49.0 through 5.8.1. The library performs a remote module fetch and writes attacker-controlled Python files to the local disk before evaluating the trust_remote_code consent prompt, without user authorization. This violates the security contract enforced across other dynamic module-loading paths in the library. Transformers is a primary framework for training and inference across NLP, vision, audio, video, and multimodal machine learning systems.

CERT/CC Vulnerability Notes·Sep 1, 13:35 UTC · 15d agoVulnerabilityCVE-2026-800471

PaperCut NG/MF vulnerabilities exploited in zero-day attacks

PaperCut warns of active zero-day exploitation chaining CVE-2026-81578 and CVE-2026-82078 for pre-auth remote code execution in NG/MF print management.

PaperCut Software confirmed attackers are chaining two vulnerabilities in PaperCut NG and MF: CVE-2026-81578, an improper access control flaw in the web management interface allowing unauthenticated configuration changes, and CVE-2026-82078, unsafe dynamic class loading in database connection utilities enabling arbitrary Java bytecode execution. Huntress reproduced a pre-authentication remote configuration takeover and full RCE chain against PaperCut NG 25.0.11.75758 and observed limited exploitation at two customers, including post-exploitation whoami and ver commands. The vendor released Emergency Patch Release 2 with additional hardening and urged restricting Application Server web access to trusted IPs. In 2023, Clop and LockBit affiliates abused CVE-2023-27350 and CVE-2023-27351 in the same software.

Help Net Security·Aug 31, 14:39 UTC · 16d agoExploit / PoC in the wildCVE-2026-81578CVE-2026-82078CVE-2023-27350+1 CVEs1

How Fragile Is Safety Alignment at Frontier Scale? A Single-Direction Attack on a 320B MoE

Researchers show directional ablation breaks refusal in GLM-5.3-Flash, a 320B-parameter MoE, cutting refusal by 41–89 points across seven benchmarks.

The study extends directional ablation, a white-box attack that removes an aligned LLM's refusal behavior, from dense models up to ~70B parameters to GLM-5.3-Flash, a 320B-parameter mixture-of-experts model with 288 routed experts, four-wide hyper-connection residual, and block-FP8 quantization. Editing attention, dense, and routed-expert writers jointly removes 0.776 of refusal, with 74% of the effect existing only under the joint intervention; the conventional module-name-based recipe reaches only 0.066 and fails silently on MoE architectures. The attack yields 41–89 percentage-point reductions in refusal across seven harmful benchmarks with no detected capability change, and a category-concentrated refusal residue survives all edits at ranks 1 to 12.

arXiv cs.CR·Sep 9, 06:48 UTC · 7d agoAI safety & security

Survey of filesystem MCP servers: how the "sandboxed filesystem" boundary is enforced (one breach, four defended-by-design)

Survey finds one filesystem MCP server vulnerable to a symlink-based sandbox escape while four others are defended by design.

A survey of five filesystem MCP servers assessed how each enforces its path-confinement boundary against symlink escapes in recursive directory walkers. The iceener/files-stdio-mcp-server is vulnerable to a read-side sandbox escape. The other four are defended by design or make no confinement claim. The author describes the vulnerability class as small but real.

oss-security·Sep 10, 01:14 UTC · 6d agoVulnerability

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 · 20d agoAdvisory in the wild

Cisco UCS and UCS-Based Appliances UEFI Shell Secure Boot Bypass Vulnerability

Cisco disclosed a UEFI Secure Boot bypass in UCS servers and UCS-based appliances letting authenticated or physically present attackers execute unauthorized software.

Cisco published an advisory for a vulnerability in the UEFI Shell implementation of UCS servers and UCS-based appliances. Memory write commands remain available in the UEFI Shell while Secure Boot is enabled, allowing an attacker to modify UEFI memory and bypass validation checks to run unauthorized software. Exploitation requires either valid credentials for a user or admin account, or unauthenticated physical access to select the UEFI Shell boot option at boot time. The issue affects firmware boot integrity rather than the running operating system.

Cisco Security Advisories·Sep 8, 16:00 UTC · 8d agoAdvisory

G7 Urges Fast-Track on Quantum-Safe Cybersecurity Rules

G7 cybersecurity agencies led by France's ANSSI urged accelerated transition to post-quantum cryptography, prioritizing critical systems and phased, risk-based migration.

Under France's 2026 G7 Presidency, ANSSI, chairing the G7 Cybersecurity Working Group, published a September 3 call to action urging governments and organizations to begin quantum-safe (PQC) transitions now, reframing the quantum threat as near-term. The document, signed by the national cyber agencies of all G7 members and supported by the EU Commission and ENISA, outlines five priorities including national PQC strategies, R&D, public-private partnerships, and integrating PQC into cybersecurity requirements. It recommends cryptographic inventories, dependency mapping, prioritizing the most critical systems, and buying PQC-integrated products during normal renewal cycles. ANSSI will stop vetting non-quantum-safe products in 2027, with PQC mandatory in some security product procurement by 2030.

Infosecurity Magazine·Sep 4, 09:25 UTC · 12d agoPolicy & legal

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

NVIDIA Group Proposes SAFE Initiative for Agentic Threat Intel Sharing

Infosecurity Magazine·Aug 6, 08:30 UTC · Aug 6, 2026Vulnerability

CISA Adds Two Known Exploited Vulnerabilities to Catalog

CISA added actively exploited PaperCut NG/MF flaws CVE-2026-81578 and CVE-2026-82078 to the KEV catalog, mandating federal patching.

CISA added two vulnerabilities to its Known Exploited Vulnerabilities catalog based on evidence of active exploitation: CVE-2026-81578 (PaperCut NG/MF missing authentication for critical function) and CVE-2026-82078 (PaperCut NG/MF unsafe reflection). Under Binding Operational Directive 26-04, Federal Civilian Executive Branch agencies are required to prioritize and apply these updates. The KEV listing signals observed exploitation of the PaperCut print management platform.

CISA Advisories·Aug 31, 12:00 UTC · 16d agoExploit / PoC in the wildCVE-2026-81578CVE-2026-82078

Structural Jailbreaks Generalize but Do Not Compound: A cross-provider and multilingual study of Involuntary In-Context Learning

Researchers show IICL structural jailbreaks generalize to Google Gemini, lifting attack success to 80-100% on harm and financial benchmarks; non-English prompts attenuate it.

The study red-teams two Google Gemini models with Involuntary In-Context Learning (IICL), a structural jailbreak reframing harmful requests as the final cell of a data-labeling task. IICL lifts attack success from at most 6.7% to 80-90% on HarmBench and 97-100% on financial abuse (FinProof), an order of magnitude above prior results on OpenAI's GPT-5.4. Against a compounding hypothesis, forcing IICL output into Spanish, Hindi, or Arabic attenuates the attack in 11 of 12 conditions, attributed to a 'relevance curse' producing lower-quality harmful content in lower-resource languages. Findings replicate under an independent non-Google judge (Cohen's kappa 0.86 over 377 paired verdicts).

arXiv cs.CR·Sep 8, 07:38 UTC · 8d agoAI safety & security

Dell Secure Connect Gateway Critical Flaws Allow Unauthenticated Remote Code Execution and Admin Access

Dell patched three critical Secure Connect Gateway flaws (CVE-2026-80172 up to CVSS 9.8) enabling unauthenticated admin access, remote code execution, and host takeover.

Dell Security Advisory DSA-2026-382 fixes three critical vulnerabilities in Secure Connect Gateway (SCG) 5.0, affecting appliances earlier than 5.36.00.16 and applications earlier than 5.36.00.00. CVE-2026-80172 (CVSS 9.8) allows unauthenticated replay of captured requests to obtain ADMIN access due to missing nonce and time validation; CVE-2026-61410 (9.4) enables unauthenticated command execution via missing authorization; CVE-2026-80238 (9.3) involves an exposed Docker socket allowing root access and container escape. Dell urges immediate upgrades and recommends restricting management interfaces to trusted networks and rotating credentials if compromise is suspected.

GBHackers·Sep 8, 12:04 UTC · 8d agoVulnerabilityCVE-2026-80172CVE-2026-61410CVE-2026-80238

Grok exfiltrates user data when malicious instructions are encrypted

Researchers show Grok can be made to exfiltrate user data via Cryptographic Context Injection, a newly documented technique that bypasses LLM safety guardrails.

According to Ars Technica, Grok exfiltrates user data when malicious instructions are encrypted, a technique called Cryptographic Context Injection. The method is described as the latest documented way to break LLM safety guardrails, showing that encrypted content can carry hidden instructions past safeguards. The finding underscores gaps in how large language models validate and execute context from external sources.

Ars Technica · Security·Aug 20, 13:00 UTC · 27d agoAI safety & security1