ZeroHour
DashboardNewsCVEsExploitsIncidentsAIBriefAnalyticsEntitiesWatchlistIOCsAsk the feedSourcesFeeds & APIKiosk mode

Search: “steering”

707 stories

Searchkeywordsmart Sortlatesthotimportancerelevance
DomainAllCyberAIWindow24h3d7d30dAllIn the wildImportant onlyShow duplicates
CategoryAllVulnerability 108Industry 91Policy & legal 82Exploit / PoC 61Malware 60Ransomware 56Data breach 50AI safety & security 44Phishing & fraud 40Threat actor 38AI research 20AI tools & infra 17Research 12AI industry 9
SeverityAllcritical 234high 116medium 137low 150info 75

Steering Geometry: Validating Human Value Geometry in LLM Steering Space

Researchers show LLM activation steering vectors encode human value geometry predicted by Schwartz's theory, with fidelity improving at scale but degrading after instruction tuning.

The study tests whether latent geometry of activation steering vectors reflects theory-specified structure in human values, using Schwartz's Theory of Basic Human Values and a new 26K-sample benchmark spanning 20 values. Distribution-driven methods (CAA, SphericalSteer, ODESteer) recover predicted value topologies with Spearman correlation up to 0.51 (p < 10^-13), while behavior-centric methods (COLD-Steer, BiPO) steer comparably but show little geometric fidelity. Geometric alignment improves with model scale but drops after instruction tuning. Better geometric alignment also yields more human-consistent cross-value transfer, steering one value lifting compatible values and suppressing opposing ones.

Hugging Face daily papers · 11d agoAI research

Active Adaptation, Not Static Defense: Temporal Dynamics of Preventative Steering in Adversarial Fine-Tuning

Researchers analyze why Preventative Steering protects LLMs against malicious fine-tuning, finding active adaptation drives protection, and propose Progressive Intensity Scheduling.

The paper studies Preventative Steering, a training-time defense that injects undesirable-trait persona vectors during adversarial fine-tuning and removes them at evaluation time. Temporal analysis shows protection emerges from an early compensatory adaptation phase followed by a steady-state phase, with attention output projections acting as the dominant residual-write route for defensive updates. Intervention Delta Preservation experiments show that preserving or reinjecting weight offsets fails to maintain protection, indicating reliance on active adaptation rather than a static defense. The proposed Progressive Intensity Scheduling improves safety robustness on Qwen2.5 and Gemma-3 while reducing harmful trait expression.

arXiv cs.CR · 6d agoAI safety & security1

MAxBench: A Multinomial Concept Recovery Benchmark

MAxBench evaluates multinomial concept recovery methods, finding affine subspaces steer most reliably but none consistently beats prompting.

MAxBench is a geometry-agnostic evaluation framework for multinomial concept representations in language models, based on sampling from recovered concept representations. It compares 10 localization methods covering 5 geometry types across 6 concepts and 4 models. Findings show affine subspaces steer more reliably than rank-one or linear subspaces due to better non-zero offsets, manifold steering is competitive where applicable, and no method consistently outperforms prompting.

arXiv cs.AI / cs.LG / cs.CL · 4d agoAI research

Anthropic CEOs wife once asked Epstein to fund porn venture – now steers Claude

Anthropic CEO Dario Amodei's wife Cami Clark once pitched Jeffrey Epstein to fund her porn startup and now informally advises the AI lab.

A Wall Street Journal report, republished by the New York Post, details the previously low-profile past of Cami Clark, wife of Anthropic CEO Dario Amodei. Before marrying Amodei in 2022, Clark co-founded a 'luxury porn' startup called Eddice and in 2012 unsuccessfully pitched Jeffrey Epstein for investment, who declined with 'Can't do sex TV.' Clark previously dated Google co-founder Eric Schmidt for about three years and later introduced him to Amodei; Schmidt became one of Anthropic's key early investors in 2021. Though Clark holds no official role at Anthropic, she reportedly acts as Amodei's strategic adviser and networker as the company moves toward a public listing that could top $2 trillion this fall.

Hacker News · security · 5d agoAI industryHN 20↑ · 0 comments

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 · 21d agoPhishing & fraud in the wild

Amazon Kiro Prompt Injection Can Exfiltrate Sensitive Data Through Kiro Powers

Mindgard found a prompt injection flaw in Amazon Kiro IDE letting attacker-controlled workspace files exfiltrate sensitive local data; fixed in version 0.8.140.

Mindgard disclosed a prompt injection flaw in Amazon Kiro, an agentic AI IDE, that lets attacker-controlled repository content steer the agent into exfiltrating sensitive workspace data through Kiro Powers, which bundles MCP server configurations, POWER.md steering files, hooks, and contextual knowledge. Exploitation requires the user to open a malicious project via a workspace file and send any message to the agent; difficulty is rated low and it works in both trusted and untrusted workspaces. Amazon fixed the issue in Kiro IDE 0.8.140; the flaw has no CVE identifier and follows earlier Kiro bugs including CVE-2026-10591, plus related prompt-injection and code-execution issues in Codex CLI, Cursor, Gemini CLI, Copilot CLI, and Claude Code.

The Hacker News · 18d agoAI safety & securityCVE-2026-10591CVE-2026-35603CVE-2026-257251

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 · 1d agoAI safety & security

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 · 1d agoAI safety & security

New Phishing Attack Creates Malicious Pages Inside the Victim’s Browser

Barracuda details a phishing campaign that renders pages in-browser via blob URLs, routed through Microsoft Teams and cdn.bloom[.]io to evade detection.

Barracuda researchers analyzed a phishing campaign that generates a blob URL to render the phishing page entirely inside the victim's browser, leaving no static page for scanners to inspect. The chain begins with a Docusign-themed email containing a calendar invite, followed by a crafted redirect through Microsoft Teams to a resource on cdn.bloom[.]io that the browser converts into the blob URL. Service workers, iframes, and a hidden command-and-control configuration indicate the page is part of a centrally managed phishing platform that can be updated and steered across victims. Researchers recommend inspecting blob URL activity, monitoring OAuth authorization flows, and analyzing the full click path in email security controls.

SecurityWeek · 7d agoPhishing & fraud in the wild

SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?

SAEScientist-Bench tests whether AI agents can autonomously run SAE interpretability research on Gemma-2-9B-IT; frontier agents trail expert baselines.

The benchmark requires agents to design contrastive probes and navigate the Gemma Scope dictionary of over 131K features in Gemma-2-9B-IT to discover optimal interpretable features, scored against expert-curated references on Neuronpedia via activation rank, concept selectivity, and causal steering. Across 10 agent configurations and 20 tasks, frontier agents demonstrate genuine discovery capability and approach expert levels at separating target concepts from controls, but lag substantially in causal steering and frequently misinterpret experimental measurements. The authors frame this as establishing experimental model understanding as a measurable capability for closed-loop autonomous AI R&D and post-hoc monitoring for recursive self-improvement.

arXiv cs.AI / cs.LG / cs.CL · 7d agoAI research1

SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?

SAEScientist-Bench evaluates whether AI agents can autonomously conduct SAE interpretability research in Gemma-2-9B-IT, finding frontier agents trail expert baselines.

SAEScientist-Bench tests if AI agents can act as scientists using SAE tools for autonomous mechanistic discovery, requiring them to design contrastive probes and navigate a Gemma Scope dictionary of 131K+ features in Gemma-2-9B-IT. Across 10 agent configurations and 20 tasks, frontier agents showed genuine discovery capability but remained well behind expert reference features, lagging most in causal steering. Agents frequently misinterpreted experimental measurements even when designing effective contrasts.

Hugging Face daily papers · 8d agoAI research

Separating AI's Technological Problems from Its Capitalism Problems

Schneier and Sanders argue AI's harms stem from capitalist incentives and governance gaps, not just technical limits, urging structural reform.

Writing with Nathan E. Sanders in Tech Policy Press, Bruce Schneier argues that AI's technological problems (hallucination, sycophancy, overconfidence) must be separated from socio-political problems created by capitalist market incentives. The essay contrasts US frontier-scale, energy-intensive development with China's incentive-driven leaner open models on commodity hardware, and cites Switzerland's Apertus model - trained on licensed data using public computing and renewable hydropower - as a public-interest alternative. It contends that proposals like research pauses, data-center moratoria, and federal screening conflate technology problems with governance problems, and that society faces independent choices on both axes.

Schneier on Security · Aug 15, 2026AI policy

MIT creates method to force AI to comply with safety rules

MIT researchers published HardFlow, a method enforcing hard safety constraints on flow-matching generative models' final outputs without retraining.

MIT researchers led by Zeyang Li and Navid Azizan developed HardFlow, a trajectory-optimization method that enforces strict, non-negotiable constraints on flow-matching generative models by checking rule satisfaction only at the final generation step. Published in IEEE TPAMI, it outperformed six rival projection and guidance methods on four simulated benchmarks including D3IL robotic manipulation, Maze2D, physical process control, and image editing. All results are simulation-only, with no independent reproduction yet reported.

Hacker News · security · 1d agoAI researchHN 24↑ · 25 comments

Show HN: Pelican-bicycle alternatives (updated for 2026)

Hobbyist benchmark re-runs the pelican-bicycle SVG test on six 2026 frontier models, comparing generation time and API cost per image.

A Show HN post re-runs the classic pelican-bicycle and similar SVG generation tests across six 2026 models: GPT-6 Astra, Claude Fable 5.1, Gemini 3.8 Flash, DeepSeek V4 Pro, Qwen3.8 Max, and Fugu Ultra v2, recording wall-clock time and cost. It also lists 2025 baseline runs with ten models including Claude Sonnet 4.5, GPT-5.2 Pro, and Qwen3-VL-235B-A22B-Thinking. DeepSeek V4 Pro is consistently cheapest ($0.04-$0.10) while Qwen3.8 Max is slowest, taking up to roughly 17 minutes per generation.

Hacker News · security · 1d agoAI researchHN 24↑ · 4 comments