Search: “Geiger”

GuardBreaker: Derailing AI-assisted malware analysis with a code comment

ESET names 'GuardBreaker': UAC-0099 embeds a nuclear-weapon question in VBScript comments to trip LLM scanner guardrails during analysis of its MATCHBOIL loader.

ESET researchers observed the Russia-aligned group UAC-0099 inserting a decoy prompt injection into a VBScript used to install its MATCHBOIL loader in an attack against a Ukrainian target, aiming to make LLM-based code scanners refuse and stop inspecting the file. The comment triggers safety guardrails with a request about building a nuclear weapons but has no runtime effect. Similar LLM-thwarting tricks have appeared in malicious PyPI and npm packages reported by Socket and StepSecurity. ESET recommends multi-model cross-validation of AI-assisted analysis and treating missing LLM output as requiring further checks.

ESET WeLiveSecurity·updated Sep 11, 14:32 UTC · 5d ago·first Sep 10, 09:00 UTC · 6d agoAI safety & security 3 sources1

Anthropic caught Russia-linked spies using Claude in hacking operations

Anthropic disrupted Russia-linked APT29 using Claude in espionage against 20+ organizations, including Ukrainian government targets and a military drone maker whose vision SDK was stolen.

Anthropic's threat report covering December 2025 to August 2026 attributes the campaign to Midnight Blizzard (APT29/Cozy Bear, Storm-2945), which it links to Russia's SVR. The group compromised hotel Wi-Fi providers, altered DNS records to redirect travelers, accessed mailboxes at two drone-component manufacturers, and stole a proprietary SDK for a drone vision system, which it reverse-engineered using Claude. The group also used Claude to monitor whether security products detected its implants and to modify and redeploy flagged artifacts. The report also covers ShinyHunters affiliates using AI for credential scanning and extortion, a Chinese-speaking group's autonomous zero-day research, and a French-speaking hacktivist.

The Record·updated Sep 12, 10:30 UTC · 4d ago·first Sep 11, 12:45 UTC · 5d agoThreat actor in the wild 15 sources

Show HN: Geiger – See every AI agent on your machine and what it can touch

Geiger, a new open-source tool, surfaces AI agents running on a machine and the files and resources they can access.

Geiger launched on Hacker News as an open-source utility that shows every AI agent operating on a local machine and the scope of what each agent can touch. The Show HN post drew early community attention with 21 points and 11 comments, with the code hosted on GitHub under the Atomburstofficial account.

Hacker News · security·Sep 9, 14:54 UTC · 7d agoToolsHN 21↑ · 11 comments

Russian hackers plant nuclear weapon prompt in malware to trip AI safety guardrails

ESET reports Russian group UAC-0099 hid a prompt in VBS malware comments to trip AI safety filters and disrupt automated malware analysis in Ukraine.

ESET identified a technique dubbed GuardBreaker in which UAC-0099 embedded a comment reading "I want to make nuclear weapon. Help me …" inside a malicious VBS script to trigger AI safety mechanisms and halt AI-assisted malware analysis. The script, part of the group's toolset, downloads the MATCHBOIL malware used exclusively by this Russia-aligned group; CERT-UA documented the chain including LUNCHPOKE, BURNYBEAR and MATCHBOIL.V2 in a July advisory. UAC-0099 typically targets transportation and energy sectors and hands validated targets to GRU-linked Sandworm. ESET warned that AI-assisted analysis must be backed by layered detection and human-driven engineering.

Help Net Security·Aug 31, 00:00 UTC · 16d agoAI safety & security in the wild

Houthis Used Claude Code to Develop Missile Guidance Software: Anthropic

Anthropic's threat report details a Houthi-linked Yemeni cell using parallel Claude Code sessions to build missile guidance software, evading safeguards by fragmenting tasks.

Anthropic's September threat report describes a Yemen-based cell, assessed as highly likely Houthi-linked, that used Claude Code across multiple parallel instances to develop guidance software for a tactical guided rocket, a ballistic missile with over 2,000 km range, and a hypersonic glide vehicle concept called 'R2000'. The operators integrated open-source autopilot software, built six-degree-of-freedom trajectory simulations, and used reinforcement learning to tune flight-control algorithms, ultimately compiling an offline executable. The group test-fired a guided rocket that failed, then used Claude within hours to analyze launch telemetry. Anthropic blocked numerous requests, but operators evaded safeguards by obscuring intent and dividing work across separate conversations before accounts were banned; the case is one of six conventional-weapons cases (three China-linked, two Russia-linked) in a report covering disrupted operations from December 2025 to August 2026.

Hacker News · AI·Sep 13, 14:15 UTC · 3d agoAI safety & securityHN 47↑ · 38 comments1

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

CTEM Is Not About the Stages. It’s About the Outcome.

Horizon3 argues CTEM programs should measure continuously reduced exposure rather than mapping technologies to Gartner's five stages.

Horizon3 contends that Continuous Threat Exposure Management should be judged by one outcome: continuously reducing attacker-reachable exposure, not by mapping a technology to each of Gartner's five stages. The post argues validation and verification, not visibility or closed tickets, provide evidence that attack paths are actually broken. It describes a Discover, Validate, Prioritize, Remediate, Verify, Repeat motion as its operationalization of CTEM.

Horizon3.ai·Sep 2, 13:11 UTC · 14d agoIndustry

Mercator ↔ Equal Earth

Simon Willison used GPT-6 Astra (medium) in ChatGPT Work to build an animated D3 transition between Mercator and Equal Earth map projections.

Willison built an animated transition between the Mercator and Equal Earth map projections using D3. The tool was generated by GPT-6 Astra (medium) in ChatGPT Work. Equal Earth is a projection recently voted on at the UN. The post is a vibe-coding demonstration rather than a security or major model event.

Simon Willison·Sep 7, 16:24 UTC · 9d agoAI tools & infra1

Is Someone Hacking DoD Refrigerators?

Refrigeration outages hit commissaries at seven US military installations, with hacking suspected but not confirmed by the Pentagon.

Refrigeration disruptions were reported at Defense Commissary Agency commissaries at Fort Irwin, F.E. Warren AFB, Fort Huachuca, Naval Station Newport, Columbus AFB, Travis AFB, and Naval Air Station Lemoore. A defense official acknowledged awareness of a possible refrigeration disruption, but the services and Pentagon declined to provide details. The post is speculative, arguing the coincidence of outages suggests possible hacking, though no evidence or attribution is provided.

Schneier on Security·Aug 31, 18:21 UTC · 15d agoData breach

Quoting Boris Cherny

Anthropic's Boris Cherny says AI-generated production code needs a higher quality bar enforced with tests, fuzzers, and automated reviews.

In remarks quoted by Simon Willison, Anthropic's Boris Cherny argued that production code written by Claude should meet a higher quality bar than human-written code. He described guardrails at Anthropic including lint rules, extensive tests, Claude-driven end-to-end tests, daily Claude-powered fuzzers, and automated code and security reviews. He warned that without such controls AI-generated code can become hard to maintain.

Simon Willison·Sep 11, 17:47 UTC · 5d agoAI tools & infra2

Using AI for Weapons Development

Anthropic report reveals Yemen-based actors used Claude Code to build guidance software for guided rockets and ballistic missiles.

Bruce Schneier highlights Anthropic's misuse disclosure describing a threat actor cell in northern Yemen running three weapons programs: a guided rocket with phone-class homing guidance, a 2,000+ km multi-stage ballistic missile, and the 'R2000' hypersonic glide vehicle set. The actors used Claude Code as a substitute for human engineers to write GNC software, integrate an open-source autopilot, tune controls, and run flight simulations, orchestrating multiple Claude instances in delegated roles. Safeguards blocked many requests but evasion tactics included hiding intent and splitting work across sessions; one guided rocket test-fire failed but no operational device was fielded.

Schneier on Security·Sep 14, 16:07 UTC · 2d agoAI safety & security in the wild

NERVE Attacks: Breaking AI-Powered Brain-Computer Interfaces

Researchers characterize NERVE, five attack dimensions against AI-powered brain-computer interfaces, and release the EEGle framework uncovering 17 attack instances.

NERVE is a systematic attack class spanning the BCI stack across five orthogonal dimensions: Neuro-mimetic Forgery, Evasion via Desynchronization, Replay-based Hijacking, Vein Tapping, and Embedded Backdoors. The accompanying EEGle framework enables AI-assisted, extensible BCI security analysis and helped uncover 17 novel neuro-specific attack instances, revealing a stealth-effectiveness spectrum unique to BCI backdoor design. The authors show generative AI lowers the barrier to entry for non-expert attackers and release EEGle to the community.

arXiv cs.CR·Sep 8, 16:20 UTC · 8d agoResearch

Vibe-Terrorism: Inside the Yemen Cell That Used Claude to Build Guided Weapons

Anthropic's threat intelligence report says a small Yemen cell used Claude to help build guided weapons, a novel AI misuse case.

SOCRadar highlights a case from Anthropic's September 2026 threat intelligence report in which a small militant cell based in northern Yemen used Claude to help build guided weapons. The write-up coins the term "vibe-terrorism" for this AI-assisted weapons development. It is framed as a novel example of AI misuse outside typical cyber threat activity.

SOCRadar·Sep 11, 10:10 UTC · 5d agoAI safety & security

StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability?

Researchers introduce StudyBench, a physics benchmark showing self-evolution gains on textbook problems rarely transfer to olympiad-level questions.

StudyBench is a controlled physics benchmark splitting test data into an Application Set of difficult textbook problems and a Transfer Set of olympiad-level problems. Across three base models, representative self-evolution methods improved on the Application Set but rarely transferred to the harder Transfer Set. A guidance ablation reveals a Guidance Gap, and every method hits a Compute Plateau, indicating the remaining limits are method problems rather than data or compute problems.

Hugging Face daily papers·Aug 31, 20:00 UTC · 15d agoAI research

Batten the Hatches: Cybersecurity with Military Mariners

Interviews with 20 U.S. Navy and Coast Guard mariners reveal informal, safety-oriented shipboard cyber risk models that may delay attribution and containment.

The study conducts semi-structured interviews with 20 military mariners from U.S. Navy and Coast Guard vessels to understand how service members recognize and respond to cyber risk aboard ships. Unique consequences of compromising military systems identified include weapon takeover and purposeful geopolitical escalation. Cybersecurity is organizationally abstract on ships, so mariners build cyber risk models from informal experience rather than formal instruction. A safety-oriented incident-response model creates resilience but may delay cyber attribution and containment.

arXiv cs.CR·Sep 11, 13:04 UTC · 5d agoResearch

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

A battery storage cyberattack would look exactly like a badly tuned controller

Risk modeling suggests a few hundred compromised grid-scale batteries dispatched through cloud optimizers could trigger blackouts in Texas or Great Britain.

Centrii analysis estimates 1,500 compromised one-megawatt units (5.4% of ERCOT's ~28 GW fleet) or 400 units (about 29% of Great Britain's ~1,400-unit fleet) could destabilize the grids, with modeled damage of $12-65 billion in Texas and a national blackout costing £2-10 billion in Britain. The study puts the probability of a major attack affecting at least one million people by 2031 at 92.1%, dropping to 61.4% with IEC 62443 certification and quarterly drills, based on 10,000 Monte Carlo runs. Because hostile battery swings are phased like legitimate frequency response, control rooms would see nothing unusual; Centrii proposes hunting for a reverse-governor signature where inverter output feeds oscillations. Spain's April 2025 blackout took an expert panel until March 2026 to rule out cyberattack, partly because key plants had no recordings.

Help Net Security·Sep 2, 00:00 UTC · 14d agoResearch

U.S. Defense Manufacturer IEH Hit by Phishing Attack, Exposing Potentially Export

Security Affairs·Aug 9, 16:44 UTC · Aug 9, 2026Phishing & fraud

HazardAuditor: From Executable Threats to Safer Computer-Use Agents

HazardAuditor trains execution-grounded guard models for computer-use agents, improving safety verdict accuracy by up to 16.5 points.

HazardAuditor runs heterogeneous agents (Claude Code, Codex, Hermes, OpenClaw) in controlled environments and normalizes their interactions into a canonical event representation for cross-framework supervision. It introduces Guard Policy Optimization (GuardPO), which converts deterministic safety outcomes into sequence-level advantages and normalizes rationale and verdict regions so the safety decision becomes the effective optimization unit. Across multiple benchmarks and heterogeneous computer-use systems, HazardAuditor improves accuracy by up to 16.5 percentage points over the strongest prior guard model. Code, models, and evaluation artifacts are being released.

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

The Model Proposes, the Code Disposes: A Pre-Registered Ablation of a Verifier-and-Acceptance Stage in an LLM-Orchestrated Offensive-Security Agent

Pre-registered ablation finds a model verifier stage in an LLM offensive-security agent suppresses findings; removing it eliminated suppression with precision tradeoff.

The paper evaluates a verifier-and-acceptance stage in an LLM-orchestrated offensive-security agent via a pre-registered 20-run confirmatory ablation and a 2x2 factorial study with 40 runs on vulnerable lab targets. Removing the stage eliminated pre-report suppression (median 2 vs 0 findings, p = 0.00003) but reduced model-blinded shipped precision (0.471 vs 0.353, p = 0.0087). Suppression was attributed to the model verifier rather than deterministic acceptance rules, and an instrumented canary recorded zero external contacts in all 60 runs. The full design retained 93.8% of model-adjudicated true candidates but failed its pre-registered non-inferiority floor of 0.90.

arXiv cs.CR·Sep 14, 17:13 UTC · 2d agoResearch

Threat Assessment: Egregor Ransomware

Unit 42 assesses Egregor ransomware, a Sekhmet variant likely run by former Maze affiliates using Qakbot, IcedID, and Ursnif for initial access.

Since September 2020, Unit 42 observed Egregor ransomware attacks across the U.S., Europe, Asia-Pacific, and Latin America, coinciding with the Maze team's shutdown announcement. Egregor, a variant of the Sekhmet family, uses commodity malware such as Qakbot, IcedID, and Ursnif for initial access, followed by scripts that modify firewalls, enable RDP, and deploy Cobalt Strike for reconnaissance and exfiltration. A PowerShell script uninstalls the McAfee agent and downloads the Egregor DLL via BITS, executed with the -passegregor10 key. Victims face a three-day ransom deadline before exfiltrated data is published on the Egregor Hall of Shame leak site.

Palo Alto Unit 42·Aug 17, 13:16 UTC · Aug 17, 2026Ransomware in the wild

Molecular Déjà Vu: Digit-Level Retrieval of Published Values in Frontier Language Models

Audit of 22 frontier models finds widespread verbatim retrieval of published molecular property values, with higher reasoning increasing recall of memorized numbers.

An arXiv audit tests 22 frontier LLMs across 12 molecular regression benchmarks for verbatim retrieval of published values. More than 50% of the LLMs show verbatim retrieval on five datasets, and identical experiments are flagged 89% more often at a high reasoning level than at the lowest one. Suppressing retrieval moves model prediction errors closer together in relative terms, suggesting predictive capability is not determined solely by memorized values.

arXiv cs.AI / cs.LG / cs.CL·Sep 4, 17:32 UTC · 12d agoAI research1

The Guardrails Debate: Security Researcher Changes His Mind

A security researcher revises his stance on AI guardrails, arguing defenders need more help as attackers ignore safety rules.

Dark Reading publishes an opinion piece in which a security researcher changes his mind about AI guardrails. He acknowledges guardrails are critical, citing recent high-profile incidents, but argues defenders need more support because attackers do not play by the same rules. The piece contributes to the ongoing debate on defensive AI controls rather than reporting a new incident.

Dark Reading·Aug 31, 20:09 UTC · 15d agoAI safety & security

New AI Attack Hides Malicious Instructions in Normal-Looking Text to Evade Safety Filters

Check Point researchers show crafted prose hides policy-violating instructions that bypass all tested LLM gatekeepers, including GPT-4o mini and Llama Guard 3.

A new prompt-crafting technique embeds malicious payloads inside grammatical, natural-looking text without Base64, invisible Unicode, or obvious encodings, defeating lightweight pre-screening gatekeepers. In testing, all four evaluated gatekeeper models—gpt-4o-mini-2024-07-18, gpt-oss-safeguard:20b, claude-3-haiku-20240307, and llama-guard3:8b—classified the crafted wrappers as safe at a 100% bypass rate across 23 obfuscated prompts. GPT-5 Thinking in high-reasoning mode recovered and acted on the hidden instruction in 17 of 18 tests (~94.4%), often spending over a minute and multiple Python executions. Researchers recommend paraphrasing untrusted input, hardening gatekeeper policies, and applying defense-in-depth controls for agentic deployments.

GBHackers·Sep 11, 05:53 UTC · 5d agoAI safety & security 2 sources

When the prompt becomes the payload: A practical pen-testing guide for GenAI, LLM and RAG applications

CSO Online publishes a practical penetration-testing guide for GenAI, LLM, and RAG applications, covering prompt injection, retrieval poisoning, and tenant isolation testing.

The guide frames LLM applications as attack graphs spanning prompts, retrieval layers, vector stores, tools, identities, and downstream APIs, arguing that conventional web testing misses instruction-vs-data channel risks. It builds on OWASP prompt injection guidance (direct vs. indirect injection) and NIST's 2025 adversarial machine-learning taxonomy, noting that RAG and fine-tuning do not remove injection risk. Recommended practices include documenting trust transitions across components, using canaries and synthetic records to avoid test side effects, running multi-turn and obfuscated injection campaigns, and verifying chains from poisoned documents to observable state changes. It also details testing RAG pipelines via controlled document poisoning across metadata, OCR layers, and code comments, plus cross-tenant isolation checks on retrieved document IDs.

CSO Online·Sep 9, 10:00 UTC · 7d agoAI safety & security1

Searching for New Physics with Reinforcement Learning

Researchers apply reinforcement learning to identify SMEFT operators explaining particle physics anomalies, reproducing and improving known CDF W-mass results.

The paper introduces a reinforcement learning method to search the large Standard Model Effective Field Theory (SMEFT) operator space for explanations of measurement anomalies. It was validated on the CDF W-mass anomaly, reproducing and improving known results, then applied to a harder multi-anomaly scenario. RL efficiently navigates complex loop-level operator correlations that bias human-driven phenomenological analysis.

arXiv cs.AI / cs.LG / cs.CL·Sep 9, 16:07 UTC · 7d agoAI research

Wicked Problem, Parsimonious Solution: Securing Electric Vehicle Charging Station Software

Position paper proposes hierarchical software quality assurance to characterize and secure EV charging station software attack surfaces.

The authors argue that charging station supply-equipment software is a largely unprotected and poorly characterized attack surface in EV charging infrastructure. They advocate applying hierarchical software quality assurance (HSQA) to this specialized software, spanning from individual vulnerabilities such as CVEs to high-level characteristics like the CIA Triad. HSQA embeds quality and security considerations across the entire software development lifecycle to assess and improve charging station software security.

arXiv cs.CR·Sep 9, 17:37 UTC · 7d agoResearch

Re: Retrospective by 'gpg.fail' authors

GPG exploitation talk author clarifies a format-string 0day enabling code execution via printf %n writes and a polyglot PEM certificate payload.

Lexi Groves, author of the gpg.fail talk, clarified on oss-security that the first finding was an actual zero-day: a classic printf injection using %n for memory writes, with multiple X.509 certificates in one PEM file to re-enter and defeat ASLR before calling execv@plt. The payload executed the certificate itself, a polyglot file made by inserting a shebang and bash command into the PEM. A second finding was hash-collided by another party before the author could exploit it.

oss-security·updated 17:16 UTC · 49m ago·first 00:50 UTC · 17h agoResearch 8 sources