Search: “chosen-brick”

Smart search ranks by meaning as well as keywords (one row per story, last 45 days).

Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks

SAILS learns to select poison sets for LLM backdoor attacks, showing attack success ranges 3% to 80% at fixed poison counts across LLaMA-3-8B settings.

The paper shows existing backdoor evaluations that randomly sample a fixed number of poisoned examples severely underestimate worst-case vulnerability: across three LLaMA-3-8B settings, attack success ranges from 3% to 80% depending only on which poison set is chosen. SAILS formalizes poison selection as oracle-budgeted set optimization, learning a set scorer from a few hundred finetune-and-evaluate runs to rank millions of candidate sets and audit a small shortlist. It improves held-out attack success by 30 percentage points over the strongest influence baselines and transfers from small-scale to full-scale finetuning, extending to code-generation, agentic, and API-only backdoors.

arXiv cs.CR·Sep 14, 04:44 UTC · 1d agoAI safety & security 2 sources

42

Iranian cyber targeting of dissidents, activists and journalists

UK NCSC, FBI, and Dutch AIVD expose CHOSEN BRICK spyware used by Iranian state actors against dissidents, activists, and journalists worldwide.

A joint advisory from the UK NCSC, FBI, and Dutch AIVD details CHOSEN BRICK, a Windows spyware family used by Iranian state cyber actors since at least 2025 against dissidents, activists, and journalists in the UK, US, and Netherlands. Actors build rapport on WhatsApp and Telegram impersonating known contacts or platform support, then deliver disguised payloads resembling apps such as Telegram, Norton, RunwayML, or fake MRI results. The malware persists via HKCU Run registry keys, adds Microsoft Defender exclusions, and uses a unique Telegram bot C2 per victim. Capabilities include screen capture, microphone recording, process enumeration, email and messaging data theft, file deletion, and system wiping; victim data has appeared on pro-Iranian leak sites.

NCSC UK·12:00 UTC · 11h agoThreat actor in the wild

78

Iranian spies hit Windows machines with Chosen Brick data-stealing malware

FBI, UK NCSC, and Dutch AIVD warn Iranian intelligence uses Chosen Brick spyware against dissidents, stealing contacts, emails, and messaging data.

A joint advisory from the FBI, UK NCSC, and Dutch AIVD says Iranian state cyber actors have used the Chosen Brick Windows malware since at least 2025 to surveil dissidents, activists, and journalists. Attacks begin with heavily researched WhatsApp and Telegram messages impersonating trusted contacts, tricking victims into opening fake installers resembling Pictory, RunwayML, Norton Antivirus, Telegram, Adobe Flash Player, and KeePass. The malware persists via the HKCU Run registry key, adds Microsoft Defender exclusions, uses victim-specific Telegram bots for C2, captures screen and audio, steals emails and Telegram/WhatsApp data, and can wipe systems.

The Register · Security·18:01 UTC · 5h agoThreat actor in the wild

68

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 · 6d agoAI research

22

CS-Guard: Benchmarking LLM Guardrails for Code Generation Security

CS-Guard benchmark shows LLM code-generation guardrails fail widely, with ~50% jailbreak ASR text-to-code and up to 100% code-to-code.

Researchers introduce CS-Guard, the first systematic benchmark for evaluating LLM guardrails for code generation security, covering text-to-code (1,000 malware-generation prompts, 7 jailbreak attacks, and a novel fictional scenario attack) and code-to-code (331 prompts across infilling, completion, and translation). They evaluate 9 guardrails across seven LLMs, finding average jailbreak attack success rates around 50% for text-to-code and 14.4% to nearly 100% for code-to-code. The fictional scenario attack achieves ASR close to 100% across many guardrails, raising reliability concerns for real-world software development. The benchmark and data are released publicly.

arXiv cs.CR·Sep 9, 06:50 UTC · 6d agoAI safety & security1

45

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 · 4d agoAI safety & security 2 sources

50

Iranian Hackers Use Telegram-Controlled Malware to Spy on Dissidents and Journalists

FBI, NCSC, and AIVD detail Iran MOIS spyware CHOSEN BRICK/HEAVYGRAM, Telegram-controlled Windows malware spying on dissidents since 2023.

A September 15 joint advisory from the FBI, UK NCSC, and Dutch AIVD attributes the Windows spyware HEAVYGRAM (NCSC name CHOSEN BRICK) to Iran's Ministry of Intelligence and Security, with the campaign dating to autumn 2023 and targeting dissidents, journalists, and activists in the UK, US, Netherlands, and worldwide. Delivered via messages impersonating known contacts or tech support, the malware assigns each victim a dedicated Telegram bot for command-and-control and exfiltration, and can take screenshots, record microphone audio, steal Telegram/WhatsApp data, saved passwords, and emails, download more malware, and wipe the computer. Persistence uses a registry Run key (SMQDService or winappx) plus Microsoft Defender exclusions, with stolen data exiting via Telegram and cloud storage services like Vultr and Storj. The US Justice Department seized four pro-Iranian leak sites in March that had published stolen victim data.

The Hacker News·16:29 UTC · 6h agoMalware in the wild

65

You Can't Prefer Emotions You Don't Sample: Intensity Undershoot in DPO-Tuned LLMs

Study quantifies DPO-tuned LLMs undershooting requested emotional intensity, tracing the gap to candidate-pool extremity rather than conditioning format.

Conditioning an instruction-tuned LLM on continuous valence-arousal targets yields gain of only 0.26 for valence and 0.13 for arousal on Llama-3.1-8B, far below faithful control of 1.0. The authors attribute undershoot to neutral-heavy preference corpora like EmoBank and candidate pools lacking extreme affect, leaving DPO without extreme exemplars. Uniform target coverage with a hotter candidate pool raises valence gain to 0.40 on Llama-3.1-8B and 0.44 on Qwen3-8B, with modest in-distribution cost; arousal gains remain unstable across seeds.

arXiv cs.AI / cs.LG / cs.CL·Sep 7, 17:47 UTC · 8d agoAI research

31

Hackers Target Claude, Cursor and Codex AI Agents to Steal Tokens and Prompt Histories

Gen Digital found infostealers like Amatera and Remus stealing AI coding agent tokens, prompt histories, and MCP configs from infected Windows and macOS machines.

Gen Digital analysts observed Amatera and Remus detections among tens of thousands of protected Windows users over three months, with Amatera targeting Cline and Continue data and Remus targeting Claude, Cursor, and OpenCode. CallbackBeaver added Cursor and Claude to its collection scope with more than 5,000 samples in 30 days, while macOS-focused Djinn Stealer has been associated with Claude, Codex, Gemini, Cline, OpenCode, and Kilo. The stealers harvest access and refresh tokens, prompt histories, and MCP configuration files that can expose source control, ticketing, databases, cloud resources, and sensitive project context for follow-on fraud. Many stealers add targets via remotely managed rules, meaning this is an adaptation of existing infostealers rather than a new vulnerability in the AI tools themselves.

Cyber Security News·updated Sep 10, 10:36 UTC · 5d ago·first Sep 9, 11:41 UTC · 6d agoMalware in the wild 4 sources2

58

Claude Fable 5.1 made me a really nice animated pelican

Anthropic launched Claude Fable 5.1, claiming gains in coding and long-running tasks, with 52.6% on Terminal-Bench-Science 0.1.

Anthropic released Claude Fable 5.1 (alongside Mythos 5.1), positioning it as a new standard for coding, knowledge work, and long-running problem-solving. The model scores 52.6% on Terminal-Bench-Science 0.1, up from 24.7% for Fable 5, versus 29.0% for Opus 5 and 22.4% for GPT-5.6 Sol. Simon Willison's hands-on test found the model produced an impressive animated pelican, though he notes other benchmarks show only slightly improved scores.

Simon Willison·Sep 1, 23:57 UTC · 13d agoModel release

82

Claude Fable 5.1's language is less "load-bearing" than its predecessor's

Arena.ai found Claude Fable 5.1 writes 30% longer answers with fewer em dashes, hedges, and validation phrases than Fable 5.

Arena.ai compared tens of thousands of high-reasoning Text Arena outputs from Anthropic's Claude Fable 5 and Fable 5.1. Fable 5.1's median answer length rose 30% to 414 words (from 319), remaining 21% shorter than Opus 5's 525. Em-dash usage fell from 16.2 to 11.0 per 1,000 words while semicolons rose to 6.09, hedges like 'perhaps' and 'arguably' dropped 36%, and praise appeared in 1.98% of responses versus 3.17%. Long content words fell from 42.6% to 38.6% and abstract nouns declined 25%, suggesting the successor's language is less 'load-bearing'.

The Decoder·Sep 10, 15:26 UTC · 5d agoAI research1

30

PentestGPT: Open-source automated penetration testing agentic framework

Open-source PentestGPT runs autonomous LLM-driven penetration tests via Claude Code and Codex, with legacy human-in-the-loop mode supporting many providers.

PentestGPT, originally published at USENIX Security 2024 by Gelei Deng and colleagues, is an open-source framework that lets a large language model autonomously run penetration testing stages (recon, exploit, walkthrough) with no human in the loop, driving Claude Code or Codex CLIs. A legacy interactive mode uses three cooperating LLM sessions maintaining a Pentesting Task Tree and supports OpenAI, Anthropic, Google Gemini, DeepSeek, xAI, Qwen, Moonshot, and local models via Ollama. The tool sends anonymous telemetry to Langfuse by default, excluding command outputs, credentials, and flags, and is available free on GitHub.

Help Net Security·Aug 12, 00:00 UTC · Aug 12, 2026Tools1

48

Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic

Multiverse Computing's Hugging Face post argues language models should refuse only the relevant subset of a topic instead of over-refusing whole subjects.

A Hugging Face blog post by Multiverse Computing examines refusal granularity in language models, arguing models should refuse the relevant subset of a topic rather than the entire topic. No full article text was available for additional technical detail.

Hugging Face Blog·Sep 8, 14:23 UTC · 7d agoAI safety & security

20

CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs

CoVeR, a training-free coverage-based token pruner, preserves 93.5% of VLM 3D-reasoning performance using only about 8% of visual tokens.

Researchers introduce CoVeR, a deterministic, training-free selector that chooses visual tokens to cover every region of a multi-view 3D scene using only token coordinates. Unlike learned-importance and voxelization pruners, it enforces an exact per-scene token budget, avoids saturation plateaus, and prevents near-duplicate selections. Experiments across four vision-language models show it surpasses prior state of the art by 3.9 percentage points on average across three 3D reasoning benchmarks.

Hugging Face daily papers·Sep 7, 20:00 UTC · 8d agoAI research

45

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

32

Claude's new system prompt really doesn't want to reproduce song lyrics

Anthropic published updated Claude consumer system prompts, including changes steering the model away from reproducing song lyrics, likely over copyright concerns.

Anthropic publishes system prompts for Claude.ai and Claude mobile apps, including historic revisions, and has reorganized them into an index with per-model pages such as the Haiku 4.5 page showing the original October 15, 2025 prompt and an updated January 18, 2026 version. The latest consumer prompt strongly discourages reproducing song lyrics, a behavioral constraint likely tied to copyright considerations. Prompts for Claude Cowork and Claude Code are not included in the published set.

Simon Willison·Sep 2, 14:16 UTC · 13d agoAI safety & security

32

Meta FAIR Introduces AI Research Preference Models (RPMs): Ranking ML Experiments Before Spending GPU Hours

Meta FAIR, Oxford and UCL introduce Research Preference Models that rank unexecuted ML experiments, lifting AIRS-Bench scores from 0.684 to 0.729 and cutting compute ~1.6×.

Researchers from Meta FAIR, Oxford, and UCL introduce Research Preference Models (RPMs), which use frozen pretrained LLMs (Qwen3.6-27B backbone, no fine-tuning) to rank unexecuted experiment candidates and execute only the winner of a pairwise knockout tournament. Two variants shipped: an inference-only LLM-as-a-judge and an agentic variant that runs small pilot experiments in an H200 sandbox. On AIRS-Bench (20 tasks, 24 hours on one H200, 10 seeds), scores rise from 0.684 (random) to 0.711 and 0.729 versus a 0.748 validation oracle, and both variants reach the baseline's 24-hour score in roughly 15 hours. The team reports new SOTA on WinoGrande (94.1% with Agentic RPM) and SVAMP (95.7% with inference-only).

MarkTechPost·Sep 6, 20:25 UTC · 9d agoAI research

45

Playco cut manual fixes 50% prototyping games with GPT-6 Astra

Game studio Playco used OpenAI's GPT-6 Astra to build three game prototypes, reporting 50% fewer manual fixes than with the previous model.

Playco, a game development company, used OpenAI's GPT-6 Astra model to generate three themed game prototypes from a single grey-box foundation. The company reports the new model cut manual fixes by 50% compared to its previous model workflow. The piece is an OpenAI-published customer story highlighting Astra's use in game prototyping.

OpenAI News·Sep 3, 12:00 UTC · 12d agoAI industry

18

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

24

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 · 6d agoAI safety & security

45

“Sorry, I can’t help with that”: How your guardrails might become the attacker’s best friend

Cisco Talos's David Bianco argues AI guardrail customization requires operational sovereignty so defenders retain the advantage over attackers.

In his first Threat Source newsletter, Cisco Talos's David Bianco explores how AI guardrails could end up aiding attackers and argues that operational sovereignty is needed when customizing them. The piece stresses that organizations should control their own AI safety configurations to keep the defender's advantage. This is commentary and analysis rather than a report of a new incident or vulnerability.

Cisco Talos·Aug 27, 18:00 UTC · 19d agoAI safety & security

22

The Pelican comparison grid for Astra is pretty interesting

Simon Willison's pelican SVG comparison shows GPT-6 Astra producing markedly better images than GPT-5.6 Sol, Terra, and Luna across reasoning levels.

Willison generated pelicans-riding-bicycles SVGs with newly accessed GPT-6 Astra at low through max reasoning levels and rendered them in a comparison grid against GPT-5.6 Sol, Terra, and Luna. Astra's outputs were markedly more coherent, while even the best GPT-5.6-Sol images remained largely abstract shapes. Astra does not support a reasoning=none setting, so all comparisons involved reasoning-enabled runs.

Simon Willison·Sep 4, 23:59 UTC · 10d agoAI research

25

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 · 4d ago·first Sep 10, 09:00 UTC · 5d agoAI safety & security 3 sources1

65

Import AI 470: No rights for machines; automating environment generation with SPADE; and building better GPU kernels with Hawkeye

METR analysis finds AI accelerating cyber vulnerability discovery, while SPADE self-play environment generation improves Qwen3 reasoning benchmark scores at 30B scale.

Import AI 470 discusses a METR research note reporting differential acceleration from AI: major acceleration in reported cyber vulnerabilities (cURL, OpenSSL, Firefox, Microsoft, NVD, OSV), minor acceleration in mathematics, and no measurable acceleration in AI-research optimization benchmarks. It also covers SPADE, a self-play framework from a multi-university team (University of Washington, Stanford, MIT, CMU, and others) that co-evolves executable training environments and agent capability using Environment Designer and Reasoning Agent roles with hint-based regret rewards. Trained on Qwen3-4B-Instruct-2507, Qwen3-8B, and Qwen3-30B-A3B-Instruct-2507 via GRPO (400 rollouts of 25 environments), SPADE lifted the 30B-A3B game-environment suite average to 58.3, +8.1 over base, and improved tool-use results across backbones. The issue also references Hawkeye for building better GPU kernels.

Import AI·Aug 24, 13:12 UTC · 22d agoAI research

42

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 · 21d agoAI research

45