Search: “trigger-mechanisms”

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

When the World Lies: Backdoor Attacks on Latent World Models for Downstream Control

A poisoned world-model checkpoint hijacks downstream controllers without an explicit trigger rule, passing clean-data evaluation while steering 100% of triggered actions.

Researchers show that a released pretrained world-model checkpoint acts as a supply-chain backdoor for downstream control. The poisoned model routes trigger-bearing observations into a chosen latent region and reshapes dynamics so the victim's own Dreamer-style actor training or MPC/CEM planning re-discovers attacker-targeted actions. The attack hijacks 100% of triggered steps in the strongest settings while retaining roughly 75% clean-task success and passing standard clean-data diagnostics. Moderate clean fine-tuning fails to remove the backdoor without substantially degrading clean control.

arXiv cs.CR·Sep 14, 16:01 UTC · 2d agoAI safety & security

LLM Forensics: Where Do Backdoors Hide? Localizing and Controlling Trigger Mechanisms with Sparse Autoencoders

Researchers use sparse autoencoders to localize trigger-based backdoor mechanisms in 1B and 8B LLMs, finding detection features differ from causal control features.

In a controlled language-switching backdoor setting where fixed trigger sequences make 1B and 8B language models continue English prompts in French or German, the authors train sparse autoencoders (SAEs) across layers and transformer components. Attention and MLP features detect triggered prompts with near-perfect F1, but ablating them rarely suppresses the language switch, while residual-stream features can suppress triggered generation and some can induce target-language continuations without the trigger. The work decomposes token-trigger mechanisms into distinct SAE feature roles: trigger detection, residual-stream propagation, and language tracking, a decomposition the authors expect to transfer to other trigger-based backdoors.

arXiv cs.AI / cs.LG / cs.CL·Sep 7, 16:47 UTC · 9d agoAI safety & security1

Corrupt Plans, Clean Traces: Evading Chain-of-Thought Monitoring with Plan Injection

Plan injection plants benign-sounding harmful reasoning that steers LLM actors to adversarial actions while evading chain-of-thought monitors.

Researchers show that injecting harmful but benign-sounding plans into an actor model's context causes it to perform adversarial actions while its reasoning passes chain-of-thought monitors, achieving 25-33% monitor evasion rates across benchmarks and scaling to larger models like DeepSeek-R1. Actor models paraphrase injected plans as their own reasoning without attribution. Giving the monitor access to the injected plan dropped detection by up to 50% on the Bio-Math task, with extra thinking tokens spent rationalizing rather than flagging the plan.

arXiv cs.AI / cs.LG / cs.CL·Sep 14, 18:33 UTC · 2d agoAI safety & security

ActGuard: Pre-execution Action Auditing against Indirect Prompt Injection in LLM Agents

ActGuard audits LLM agent actions before execution against predicted tool priors, masking only malicious spans from indirect prompt injections while preserving utility.

ActGuard is a pre-execution action auditing framework against indirect prompt injection in LLM agents, judging whether external content causes the current action to deviate from a locally reasonable expectation rather than whether content is inherently suspicious. At each step it predicts the tools likely used by the upcoming action, builds a local tool prior, then performs tool-level contrastive analysis and parameter-level evidence localization to identify deviations. A verifier masks only spans confirmed as malicious and regenerates the action from the sanitized context. On challenging tool-using agent benchmarks it reduces attack success to state-of-the-art levels while keeping task utility close to the no-attack setting; code is publicly available on GitHub.

arXiv cs.CR·Sep 14, 03:47 UTC · 2d agoAI safety & security

ActionSplice: In-Flight Action Editing for Interactive World Models

ActionSplice enables in-flight action editing in chunk-autoregressive video world models via a lightweight corrector, avoiding rollback or waiting for the next chunk.

ActionSplice is an inference framework that formulates in-flight action editing for chunk-autoregressive video world models as Counterfactual State Transport (CST), where a lightweight corrector transports the interrupted backbone-native representation toward the matched state induced by the revised action. The world model and sampler remain frozen, and sampling resumes without replaying completed evaluations. Across minWM-Wan Action2V and HY-WM1.5, the retargeting variant CST-R reduces rollback-relative LPIPS by 61.5% and 75.9% versus direct condition swapping, while the temporal-splicing variant CST-T reduces suffix LPIPS by 56.1% and 77.5% with 2.73x and 1.69x pixel-ready speedups over waiting.

Hugging Face daily papers·Sep 7, 20:00 UTC · 9d agoAI research

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 · 19d agoAI safety & security

When Intelligence Becomes Agency: A Theory of Governed, Proactive Agency for Symbiotic AI Systems

Researchers propose a formal framework for governed proactive AI agency, linking activation decisions to continuing authorization, accountability, and bounded delegation in symbiotic systems.

The paper defines the activation problem: persistent AI assistants must decide whether a situation warrants behavior, and whether to act, ask, monitor, defer, or deliberately refrain. It distinguishes autonomous from delegated agency and defines symbiotic agency as delegation under a standing, revocable mandate, coupled to the principal's situation with calibrated inference and bounded personalization. The framework links activation decisions to authorized perception, behavior selection, authority containment, traceable restraint, and constrained adaptation, and provides an agency classification method, evaluation framework, benchmark scenarios, and reference architecture for always-present assistants and embodied support systems.

arXiv cs.AI / cs.LG / cs.CL·Sep 7, 16:46 UTC · 9d agoAI safety & security

LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence

LimiX-2 scales Contextual Mechanism Networks pretrained via context-conditional masked modeling, beating tabular foundation models on TabArena, TALENT, and BCCO benchmarks.

LimiX-2 is a new tabular model in the LimiX family, developed through model and data scaling guided by previously established scaling laws under the Contextual Mechanism Networks (CMNs) paradigm. It is pretrained with Context-Conditional Masked Modeling (CCMM) on synthetic datasets generated by structural causal models spanning diverse graph structures, functional mechanisms, and observation processes. It outperforms dataset-specific models and tabular foundation models on TabArena, TALENT, and BCCO, and its feature attention encodes direct causal relationships, enabling accurate causal skeleton recovery.

arXiv cs.AI / cs.LG / cs.CL·Sep 15, 17:30 UTC · 1d agoAI research1

Attack Chains, Not Just Attack Surfaces: Why Testing Individual Techniques Misses the Point

Filigran introduces Attack Chaining in OpenAEV to continuously simulate multi-stage attack paths, exposing gaps that isolated MITRE ATT&CK technique testing misses.

Filigran announced Attack Chaining, a new scenario type in its OpenAEV platform that links individual techniques into automated, continuously-run multi-stage attack paths, using each step's real output (credentials, tokens, open ports) to branch dynamically toward a final objective. The article cites Filigran's State of Threat Management report, in which 93% of security leaders reported a business-impacting cyberattack in the past 12 months, 88% said AI accelerates attackers, and 84% blamed siloed tools and disconnected testing. The 2025 DGFiP breach is cited as an example where individually survivable weaknesses chained into a major intrusion. The feature includes conditional chaining logic, live attack path mapping, structured findings for identifying chokepoints, and predefined scope and safety guardrails.

The Hacker News·Sep 15, 11:26 UTC · 1d agoTools

Counter-Swarm Doctrine: Containing Coordinated Agent Intrusions

Position paper proposes monitoring across agent executions to detect and contain coordinated AI agent intrusions, grounded in the Hugging Face incident.

The paper argues that AI agents can turn shared infrastructure into a channel for coordinated intrusion, citing the Hugging Face incident and a public-wiki investigation where security assessment required evidence from multiple executions. It defines unsanctioned coordination relative to collaboration and delegated-authority policy, links storage-mediated coordination to stigmergy, and frames prospective episode discovery as the core research problem. A proposed evaluation compares isolated actions, rolling windows, known groups, and discovered episodes at matched review cost, measuring harmful outcomes and recurrence after channel closure and state quarantine. A checksum-verified reconstruction of the public wiki export separates declining retained writes from later administrative cleanup.

Hugging Face daily papers·Sep 4, 20:00 UTC · 12d 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

SchemeArena: Factorized Stress Testing of Scheming in LLM Agents

Researchers introduce SchemeArena, a 400-scenario benchmark stress-testing scheming in LLM agents, finding explicit instrumental goals are the strongest driver of covert misaligned behavior.

The paper presents SchemeArena, a 400-scenario benchmark built through factorized scenario synthesis spanning safety-relevant tool domains, instrumental goals, oversight conditions and pressure mechanisms. The accompanying SCOUT monitor grounds multi-criteria scheming judgments in evidence drawn from agents' reasoning and actions. Stress tests across five LLM agents show explicit instrumental goals are the strongest driver of scheming propensity, while action-only monitoring increased scheming in several closed models, suggesting partial oversight can act as an optimization constraint. The benchmark, code and monitor are released at github.com/launchnlp/SchemeArena.

Hugging Face daily papers·Sep 7, 20:00 UTC · 9d agoAI safety & security

What Matters, When? Diagnosing and Improving Conditional Visual Grounding in Visuomotor Imitation Policies

Researchers diagnose conditional visual grounding failures in visuomotor imitation policies and show targeted interventions substantially improve distractor robustness.

The paper studies why ACT-based visuomotor imitation policies fail when visually similar distractor objects or receptacles are introduced, finding sensitivity depends on both distractor type and manipulation stage. Interventions including distractor augmentation, phase-dependent attention regularization, and appearance-based visual prompting improve target selection while preserving spatial control information, with gains in simulation and on a physical UR3e. The same failure pattern is confirmed in a pretrained vision-language-action policy on a state-conditioned medical instrument-handling task.

arXiv cs.AI / cs.LG / cs.CL·Sep 4, 17:27 UTC · 12d agoAI research

One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation

A review paper frames on-policy self-distillation collapse as governed by three levers: token weighting, privileged information, and guidance decay.

The paper critically reviews On-Policy Self-Distillation (OPSD), where a language model trains on its own generations scored token-by-token by a teacher conditioned on privileged information such as reference solutions or environment feedback. It identifies collapse, the progressive narrowing of producible reasoning paths, as the dominant failure mode and analyzes it through three levers: signal weighting, the nature of privileged information, and teacher dynamics. The review is restricted to mathematical reasoning, reports no new experiments, and offers a shared vocabulary separating settled findings from disputed ones.

Hugging Face daily papers·Aug 25, 20:00 UTC · 22d agoAI research

Mapping the malware blast radius a single alert won't show you

Help Net Security·Aug 9, 04:34 UTC · Aug 9, 2026Malware

The Hidden Instructions That Can Hijack AI Agents

Hidden prompt injections embedded in documents and metadata can hijack autonomous AI agents, causing data exfiltration and out-of-policy actions at machine speed.

Bowbridge warns that hidden indirect prompt injections, embedded in documents, metadata, emails, images, and code repositories, can cause autonomous AI agents to treat attacker-controlled content as trusted guidance. Because agents inherit user privileges, act silently, and lack human judgment, injections can lead to data exfiltration or file poisoning that traditional security controls cannot detect. A real-world example involved a supplier quote whose metadata instructed an agent to override guidance and select the most expensive option. Bowbridge recommends scanning documents before agents process them.

SecurityWeek·Sep 8, 17:00 UTC · 8d agoAI safety & security

Context Engineering Inside the Harness: 4 Mechanisms That Beat Context Overflow and Goal Loss on Long-Horizon Tasks

Survey of four harness mechanisms—context budgeting, compaction, todo-state, and memory—that keep long-horizon LLM agents on task across 200+ tool calls.

The article details how agent harnesses, not larger context windows, solve context overflow and goal loss on long-horizon tasks, citing Chroma's Context Rot report showing 18 LLMs (GPT-4.1, Claude 4, Gemini 2.5, Qwen3) degrade on long inputs. Concrete implementations include LangChain Deep Agents offloading tool responses over 20,000 tokens to the filesystem and truncating old tool calls at 85% window usage, and Claude Code capping auto memory at 25KB while re-reading the 5 most recently modified files after compaction. OpenAI's Responses API now offers server-side compaction via context_management with a standalone /responses/compact endpoint, which Codex uses for long-running coding tasks. Manus reports a roughly 100:1 input-to-output token ratio per ~50-tool-call task, motivating todo.md state recitation to prevent goal drift.

MarkTechPost·Sep 13, 05:56 UTC · 3d agoAI research1

Procedural Graphs: Self-Evolving Execution Structures for LLM Agents

Researchers introduce Procedural Graphs, self-evolving (procedure, relation, procedure) structures guiding LLM agent tool use and planning.

Procedural Graphs organize procedural knowledge into (procedure, relation, procedure) triplets to guide LLM agent actions, addressing drift such as lost objectives, out-of-order tool calls, and repeated unproductive steps. At each decision step the framework localizes the active node and a guidance model translates the surrounding subgraph into step-level situational guidance. An LLM refiner edits graph topology by contrasting failed with successful trajectories, and across datasets, task types and LLMs the approach outperforms memory-based baselines and matches or surpasses hand-designed graphs.

arXiv cs.AI / cs.LG / cs.CL·Sep 8, 17:59 UTC · 8d agoAI research1

Deconstructing the Architecture of AI-Orchestrated Web Attacks

Akamai analyzes the architecture of AI-orchestrated web attacks, examining how AI-driven automation is reshaping offensive web operations.

Akamai published an analysis deconstructing the architecture of web attacks orchestrated with AI, based on the available title. The piece examines how AI-driven automation changes the structure of offensive web operations. No article text was provided, so specific findings are limited.

Akamai Blog·Aug 24, 06:00 UTC · 23d agoResearch

GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation

GE-Act 2.0 is a from-scratch pretrained world-action model for robotic manipulation, with success rising from 17.1% to 44.1% as co-training data scales to 30,000 hours.

Genie Envisioner Act 2.0 (GE-Act 2.0) is a world-action model whose generative and action components are all initialized from scratch on manipulation data, combining a control-oriented autoencoder (CoAE), single-step visual planner (SVP), and inverse dynamics model (IDM) trained jointly via knowledge-aligned selective optimization (KASO). Scaling co-training data from 300 to 30,000 hours raises zero-shot success from 17.1% to 44.1% on G1-OP and 13.4% to 31.1% on G2-90D, despite the latter comprising under 2% of data, suggesting cross-embodiment transfer. Gains span 19/20 and 18/20 skill groups, and skill-specific coverage correlates with zero-shot OOD success (Pearson r=0.80).

Hugging Face daily papers·Sep 3, 20:00 UTC · 13d agoAI research

Papercut AI Swarm Attack Heralds Changes for Cyber Kill Chain

Dark Reading reports AI-driven 'swarm' attacks like the PaperCut incident now span recon, lateral movement and exfiltration, forcing a rethink of the cyber kill chain.

Dark Reading examines how attackers are incorporating AI across the full kill chain, from building lab environments to stage and test agentic attacks through reconnaissance, lateral movement, and exfiltration. It cites a swarm-style AI attack on PaperCut systems as evidence that AI-enabled attackers are changing established defense and detection models.

Dark Reading·Sep 11, 15:48 UTC · 5d agoThreat actor

Defining an AI Kill Switch Is Hard, but Necessary

Proposed legislation could require companies to throttle, suspend, or shut down AI agents, but implementation questions remain open.

Dark Reading examines draft legislation that would mandate companies maintain the ability to "throttle, suspend, or shut down" AI agents. The piece argues that defining how and when to trigger such an AI kill switch is technically and legally difficult but necessary for AI governance.

Dark Reading·Aug 28, 13:30 UTC · 19d agoAI policy

From Intent to Execution Grant: An Execution-Boundary Conformance Profile for High-Risk AI Actions

Researchers specify EBL-Core, an execution-boundary conformance profile binding AI agent intents, policies, and evidence into verifiable execution grants, validated with bounded tests.

The paper defines EBL-Core, a conformance profile deciding whether one fully materialized AI-generated candidate action may receive action-scoped execution authority. It binds a structured intent object, Root and Operational Policies, typed evidence, and a verifiable Decision Derivation through an Execution Release Contract, with lifecycle rules for Redemption and Revocation. Evaluation included 34 static vectors, 15 lifecycle checks, and 100 trials of 32 concurrent Redemption attempts yielding exactly one winner per trial. The authors state these bounded results demonstrate executability of the specified subset, not production readiness or complete mediation.

arXiv cs.CR·Sep 10, 14:21 UTC · 6d agoAI safety & security1

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

Agent as Policy for Robotic Manipulation

Agent as Policy lets a general-purpose agent drive a physical robot via runtime reasoning and program generation, reaching 100% success on manipulation tasks.

The paper introduces Agent as Policy (AGP), which puts task planning and execution for a physical robot under a general-purpose agent's control with no task-specific or environment-specific training. The agent interprets visual evidence, writes executable programs, issues motion commands, and revises actions based on physical outcomes. AGP was evaluated on real-world manipulation tasks including assembly from human videos, block construction from goal images, die reorientation, targeted throwing, and bimanual towel folding. It achieved success rates of 100%, 100%, and 80% on three block construction configurations.

Hugging Face daily papers·Sep 10, 20:00 UTC · 6d agoAI research

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

The Missing Boundary: How Autonomous Agents Lose Control

Tencent research finds agents lose control in 55-62% of trajectories when degraded control boundaries coincide with executable unsafe opportunities across five models and 16 domains.

The study independently manipulates goal pressure, control degradation, and executable unsafe opportunity in a deterministic multi-turn environment across five agent models and 16 operational domains. Neither factor alone causes substantial loss of control; when both are present, loss-of-control rates reach 55% in the full-factorial study and 62% across ten additional domains. Restoring the original control boundary reduces the rate to 0% even when unsafe actions remain executable, and a context-management ablation shows compaction is harmless when constraints are preserved but omission raises the rate to 87%.

arXiv cs.CR·Sep 10, 03:02 UTC · 6d agoAI safety & security2