ZeroHour
DashboardNewsCVEsExploitsIncidentsAIBriefAnalyticsEntitiesWatchlistIOCsAsk the feedSourcesFeeds & APIKiosk mode

Search: “erdosbench”

27 stories

Searchkeywordsmart
DomainAllCyberAIWindow24h3d7d30dAllIn the wildImportant onlyShow duplicates
CategoryAllAI industry 1
SeverityAllcritical 0high 0medium 0low 0info 1

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

GPT-6 Astra gives mathematicians a breather, and OpenAI says that's by design

OpenAI's GPT-6 Astra tops ulam.ai's ErdosBench math benchmark with 106 of 226 problems solved, while the company prioritizes recursive self-improvement over math optimization.

OpenAI's GPT-6 Astra leads ulam.ai's ErdosBench with a score of 3.23, solving 106 of 226 open math problems and fully solving 43, ahead of GPT-5.6 Sol's 78 solved problems. Chief scientist Jakub Pachocki said OpenAI deliberately avoided targeted math optimization to prioritize recursive self-improvement and automated alignment research. Benchmark developer Przemek Chojecki estimated the gain at 5-10% across tested math-research skills. Mathematician Terence Tao warned at the 2026 International Congress of Mathematicians that AI-generated proofs could shift mathematics from proof scarcity to proof overload.

The Decoderupdated · 5h agofirst · 6d agoAI industry 11 sources1

Chaotic Eclipse Released GreenSection, A PoC For NVIDIA Memory Corruption Zero-Day

Researcher Chaotic Eclipse released GreenSection, a PoC exploiting an unpatched out-of-bounds write in NVIDIA Windows user-mode shared memory.

Security researcher Chaotic Eclipse disclosed an out-of-bounds write in NVIDIA's Windows user-mode components, which share a global memory section (\BaseNamedObjects\{52813408-3561-4705-820a-2b3b78be92ba}) with full read/write access to all users. The PoC crashes applications running Vulkan or OpenGL; the researcher says the bug could cross user boundaries or compromise dwm.exe but did not fully assess the impact. No CVE has been assigned and no patch is mentioned. The researcher recently released zero-day PoCs against Kaspersky, Avast, and CrowdStrike Falcon.

Security Affairs · 9d agoExploit / PoC 2 sources

Hackers Weaponize AI Safety Guardrails to Hide Malware From LLM-Powered Security Scanners

ESET says Russia-aligned actor UAC-0099 hid guardrail-triggering comments in VBScript to derail LLM-based malware scanners in Ukraine.

ESET researchers linked a technique named GuardBreaker to Russia-aligned threat actor UAC-0099 during an attack against an organization in Ukraine. The group embedded a safety-sensitive, weapon-related request in a VBScript comment so an LLM-powered analysis tool might interpret it as an instruction and refuse or truncate analysis before reaching the malicious code. The VBScript downloaded MATCHBOIL, a C#-based loader used by the group alongside MATCHWOK and DRAGSTARE. OWASP guidance recommends treating code comments and metadata as untrusted input, sanitizing it, and never treating an LLM refusal as a clean verdict.

GBHackersupdated · 5d agofirst · 5d agoThreat actor in the wild 3 sources1

KREMLIN Banking Malware Hijacks Chrome and Edge to Steal Credentials and Session Tokens

Elastic Security Labs details KREMLIN, Brazilian banking malware using malicious Chrome/Edge extensions and Ethereum smart contracts to steal credentials and session tokens.

Elastic Security Labs documents KREMLIN (tracked as REF9334), a Brazilian banking malware toolkit active since at least May 2025 that impersonates a dozen Brazilian banks. It uses multi-stage JavaScript loaders, a C++ installer that DLL-sideloads via a legitimate SentinelOne binary, and a malicious Chrome/Edge extension named 'AVSync System Inc.' Ethereum smart contracts act as dead-drop resolvers for C2 endpoints, a shift that occurred May 19, 2026, making infrastructure hard to disrupt. The extension harvests cookies, sessionStorage/localStorage, browsing history, screenshots, and full page HTML via WebSocket plus CSS-disguised polling endpoints. The group has run seven distinct campaigns and also distributes Pulsar RAT and Remcos RAT.

The Hacker Newsupdated · 13h agofirst · 1d agoMalware in the wild 2 sources

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 · 15d agoAI research

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 · 5d agoAI research

StochBench: A Domain-Specific Benchmark for Stochastic Processes in Lean

StochBench introduces 450 graduate-level stochastic-processes problems in Lean 4; an Opus 4.8-based agent proved 34.9% under a 15-minute limit.

StochBench is a Lean 4 benchmark of 450 graduate stochastic-processes problems, each paired with its natural-language source, covering Markov chains, renewal processes, martingales, Brownian motion, stochastic calculus, weak convergence, and Poisson and continuous-time Markov processes. The benchmark addresses field-specific applied mathematics underrepresented in Mathlib, unlike competition-math-dominated suites such as IMO and Putnam collections. An Opus 4.8-based agent achieved a 34.9% proof rate (157/450) under a 15-minute per-problem limit, showing the benchmark remains challenging for advanced provers.

Hugging Face daily papers · 8d agoAI research

Towards Standardized Evaluation of GPU Memory Safety with GMSBench

GMSBench provides 149 CUDA tests covering spatial, temporal, and concurrency GPU memory errors, exposing detection gaps in Compute Sanitizer.

GMSBench is a GPU memory safety benchmark comprising 149 self-contained CUDA tests spanning spatial, temporal, and concurrency errors across different GPU memory spaces and execution scenarios. The authors evaluate NVIDIA's Compute Sanitizer across multiple GPU architectures using the suite, exposing gaps in its detection coverage. The benchmark offers a standardized foundation for comparative evaluation of GPU memory safety mechanisms.

arXiv cs.CR · 8d agoResearch

MicroHasTEE: Bare-Metal Haskell for Type-Level Peripheral Ownership on Armv8-M

MicroHasTEE expresses TrustZone secure and non-secure firmware as one typed Haskell program, catching peripheral-ownership inconsistencies at compile time.

MicroHasTEE is a multiparty Haskell framework that models both TrustZone firmware images as participants in a single typed program, using type-level capability ledgers to track peripheral acquisition, configuration, transfer, and finalization. MicroHs compiles the shared program twice to produce separate bare-metal Secure and Non-secure firmware images. The framework rejects inconsistent resource use, post-configuration attribution changes, wrong-domain callbacks, and calls to unregistered Secure services. A door-lock case study on an STM32U5 Nucleo board produced images of 232.7 KiB and 228.4 KiB of flash with roughly 220 KiB of SRAM per domain.

arXiv cs.CR · 5d agoResearch1

xDailyBench: Benchmarking LLMs on Professional Consultation for Real-Life Problems

xDailyBench tests 11 frontier LLMs on 248 real-life consultation tasks; the best models score 75.6% and lag on implicit requirements.

The benchmark spans 51 scenarios across personal life, white-collar work, learning and research, and cross-domain activities, grounded in requests users actually completed or intended to complete with AI. Tasks are scored with fine-grained binary rubrics covering explicit and implicit requirements under standardized agentic settings. Across 11 frontier models, the best achieved a 75.6% task-level score, with all models performing at least 9 percentage points worse on implicit than explicit requirements.

arXiv cs.AI / cs.LG / cs.CL · 9d agoAI research

Redtail Payload Analysis [Guest Diary], (Wed, Sep 9th)

SANS guest analyst detonated a RedTail Linux sample from a DShield honeypot, finding process masquerading as php-fpm, monitoring-kill behavior, and a TCP listener.

A DShield honeypot captured multi-architecture RedTail Linux executables (ARM, ARM64, i686, RISC-V, x86-64) deployed via shell scripts. Dynamic analysis of the UPX-packed, statically linked x86-64 sample (SHA-256 63be5f38...d35e) in an isolated Ubuntu 24.04 VM on Proxmox showed it renamed its process via prctl(PR_SET_NAME), killed a filesystem-monitoring process, and opened a TCP listening socket while surviving processes posed as php-fpm or PostgreSQL-like workers. Differential memory images pre- and post-execution were captured from the hypervisor for forensics.

SANS Internet Storm Center · 6d agoMalware in the wild1

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 · 16d agoAI safety & security in the wild

Anthropic Users Hit by Infostealer Attacks, Session Thefts

A threat actor used multiple infostealers to harvest session data and hijack Claude accounts belonging to an unknown number of users.

Dark Reading reports that a threat actor deployed a variety of infostealer families to collect session information, which was then used to access Claude accounts belonging to an unknown number of users. Anthropic has not disclosed the scale of the compromise. The incident underscores session token theft via infostealer logs as an effective route into AI platform accounts.

Dark Reading · 15d agoMalware in the wild

EVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness?

Researchers introduce EVOHARNESSBENCH, a benchmark showing that evolving agent harnesses (tools, skills, agents) cause forgetting and inconsistent adaptation across 802 tasks.

The paper introduces EVOHARNESSBENCH, a benchmark that places non-stationarity in the externally supplied agent harness rather than in the task stream, evaluating agents across tools, skills, and specialist agents. It comprises 17 multi-stage harness streams built deterministically from verifier-based benchmarks, totaling 802 tasks, 520 tools, 42 skills, and 62 agents. Evaluation covers deployment (retention of previously accessible competence) and self-evolving adaptation settings. Results show harness expansion alone degrades previously solved tasks (harness-induced forgetting), adaptation gains are inconsistent, and retention and adaptation can pull in opposite directions.

Hugging Face daily papers · 13d agoAI research

27.5KB language-agnostic WebGPU syntax highlighter

A developer released gpu-lexer, a 27.5KB language-agnostic syntax highlighter that uses a tiny WebGPU model to label code tokens in the browser.

gpu-lexer splits source into words, whitespace, and symbols, then a small WebGPU model uses local and whole-file context to assign nine token classes, working on languages never seen in training. On held-out files, 12.57% of token labels differ from Shiki, though this measures agreement with Shiki rather than objective correctness. In benchmarks against Shiki 4.4.3, Prism.js, Highlight.js, Sugar High, and Starry Night, it highlighted 10 concatenated copies of three.min.js (5.56M characters) about 10x faster on an Apple M4 Pro in Chrome 152. The author frames it as an experiment, not a grammar-equivalent highlighter.

Hacker News · security · 7d agoAI tools & infraHN 21↑ · 5 comments1

Campaign Evolution: pseudo

Unit 42 traces the pseudo-Darkleech campaign's 2016 shift from Angler to Neutrino to Rig exploit kits and rotating ransomware payloads.

Unit 42 documents how the pseudo-Darkleech exploit kit campaign evolved through 2016, switching from Angler EK to Neutrino EK in June and to Rig EK in September after Neutrino ceased operations. Payloads rotated from TeslaCrypt to CryptXXX, CrypMIC, and finally Cerber ransomware by October 2016. Injected script on compromised websites changed from 12,000-18,000 character obfuscated blocks to short, unobfuscated hidden iframes starting July 1, 2016.

Palo Alto Unit 42 · Aug 17, 2026Threat actor in the wild

BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender

Blender-VideoBench evaluates agentic video understanding by having agents programmatically reconstruct real videos in Blender scenes.

BVB (Blender-VideoBench) tests whether multimodal agents truly understand videos by requiring programmatic reconstruction of real-world videos as animated Blender scenes via a lightweight Mini-BVB harness under identical sandbox and cost constraints. Evaluation uses Dual VQA for spatiotemporal fact preservation and Latent Similarity for perceptual match, combined in a square-root mean overall score. Across 51 configurations from 10 model families, the best model reaches 88.6 Latent Similarity but retains only 53.7% of source-correct spatiotemporal answers, showing semantic retention remains the main challenge.

Hugging Face daily papers · 2d agoAI research

You've Got a BUD in Me: Authenticated Reads from Per-Block Write Logs

Researchers propose BUD, per-block write-log digests enabling blockchain validators to serve historical membership and exclusion proofs far cheaper than state-wide tries.

The paper introduces Block Update Digests (BUD), which authenticate each block's write log with predecessor pointers, plus a SuperBUD and exponential hierarchy to turn long unchanged intervals into short proofs. Soundness against adversarial provers and up to f Byzantine validators is proven under archive, attestation, and committee evidence assumptions. Benchmarks show a 50x state-size increase raises the base-BUD path only 1.24x versus 3.1x for in-memory and 69.5x for disk-backed Merkle Patricia tries, with read payloads below 800 bytes and p99 warm verification at 146 microseconds.

arXiv cs.CR · 6d agoResearch

MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes

MetroLLM-Bench is a 955-case benchmark testing language models as transit kiosk tool-calling runtimes across six real metro systems.

The benchmark covers 37-414-station metro systems and eleven task categories including routing, fare calculation, disruptions, accessibility, and adversarial input, with 14 deterministic and 8 semantic scoring components. Of 26 models from six vendors, a PEFT-tuned 4B Qwen 3.5 student scored 91.3 on Tier 1, exceeding GPT-5.6 (90.6/90.0), while Muse Glimmer 30B led the composite ranking. A deterministic rule-based baseline reached 84.6, and PEFT gains over base models shrank from +7.03 points at 2B to -0.91 at 27B.

Hugging Face daily papers · 7d agoAI research

Eleethub: A Cryptocurrency Mining Botnet with Rootkit for Self

Unit 42 uncovered Eleethub, a Perl-based Bitcoin mining botnet using a crafted rootkit and libprocesshider to evade detection, still under development with few infections.

Unit 42 discovered an under-development Perl Shellbot campaign that mines Bitcoin using xmrig and emech while evading detection via a rootkit that replaces the ps tool and the LD_PRELOAD-based libprocesshider.so library. Infected devices download a malicious shell script, connect to IRC-based C2 at eleethub.com and the UnderNet network, and can receive commands for UDP/TCP floods, port scans, and HTTP attacks. The botnet can affect Unix systems and Windows 10 hosts running a Linux subsystem, and its operators use the 'Los Zetas' branding, though they are unlikely to be the Mexican drug cartel. Researchers found only a few compromised 'zombies' before the campaign expanded.

Palo Alto Unit 42 · 28d agoMalware in the wild

Fortunate Recall: Ontology-Driven Memory Lifecycle Management for Persistent Coherence in LLMs

Fortunate Recall introduces ontology-based lifecycle policies for LLM memory, cutting confabulation roughly in half (e.g., 45.1% to 22.4%) versus Mem0.

Fortunate Recall (FR) is a composable policy layer that classifies personal facts into a 10+1 behavioral ontology and applies category-specific lifecycle rules including differential temporal decay, slot-key supersession, event-time validity, and retrieval routing. FR-Bank scores 76.9% on the new 516-question LifecycleBench, ahead of Mem0, A-MEM, Memory-R1, and MemoryOS (61%-70.5%), and 75.2% on LongMemEval-S. End-to-end, confabulation drops from Mem0's 45.1% to 22.4% over answered queries, with the ranking replicating on open-weight Kimi K2.5 and transferring to the independent BEAM benchmark (46.8% vs 32.9%).

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

IT help-desk vishing tricks executives into handing over Microsoft 365 access

Arctic Wolf tracks PREY-0058 (linked to UNC6671), a vishing campaign stealing Microsoft 365 session tokens via AiTM panels for SaaS data theft and extortion.

Arctic Wolf is tracking a campaign, PREY-0058, sharing tradecraft with Google Threat Intelligence Group's UNC6671, in which callers posing as internal IT talk employees through fake passkey/MFA setups. Operator-controlled adversary-in-the-middle pages harvest passwords and MFA approvals to seize session tokens, then actors enumerate and bulk-exfiltrate data from SharePoint, OneDrive, Exchange, and Box. Extortion brands include BlackFile, Pink, Helix, Cinder, and Redact; targets are mostly US-based executives in construction, healthcare, real estate, finance, and professional services, with exfiltration shifting to residential proxies like NodeMaven.

Help Net Security · 8d agoThreat actor in the wild1

Keys to the Kingdom: Erlang/OTP SSH Vulnerability Analysis and Exploits Observed in the Wild

Attackers actively exploit CVE-2025-32433, a CVSS 10.0 unauthenticated RCE in Erlang/OTP SSH, heavily targeting OT and critical infrastructure networks.

CVE-2025-32433 enables unauthenticated RCE in Erlang/OTP's SSH daemon via SSH connection protocol messages (codes >= 80) processed before authentication, affecting versions before OTP-27.3.3, OTP-26.2.5.11 and OTP-25.3.2.20. Unit 42 recorded a spike in exploitation between May 1-9, 2025, with 70% of detections on firewalls protecting OT networks, disproportionately affecting healthcare, agriculture, media and high technology. Observed payloads bind TCP-connected shells or launch Bash reverse shells to hosts like 146.103.40.203:6667, with randomized DNS lookups under dns.outbound.watchtowr.com indicating OAST-driven blind RCE validation.

Palo Alto Unit 42 · Aug 17, 2026Exploit / PoC in the wildCVE-2025-32433

Honeypot-Omaha and batch.py [Guest Diary], (Wed, Sep 2nd)

A SANS ISC guest diary describes batch.py, a Python tool that consolidates honeypot logs and enriches IOCs with threat intelligence data.

Written by a SANS.edu BACS intern, the diary explains analysis of the DShield Honeypot-Omaha sensor, which uses Cowrie to emulate SSH and Telnet and log attacker activity. The author's batch.py script implements a four-phase pipeline with SHA-256-generated master and guest authentication to consolidate JSON and log files, correlate data via external APIs, and produce MITRE, CVE, geolocation, threat-score and fingerprint enrichment for investigated indicators.

SANS Internet Storm Center · 13d agoTools1

τ^τ-Bench: An Environment for End-To-End, Realistic Agent Construction

New τ^τ-bench tasks coding agents with building deployable customer-service agents; best config, Claude Opus 5, passes only 23.9% of simulations.

Researchers introduce τ^τ-bench, an end-to-end benchmark where a developer agent must build a complete customer-service agent from real business records, a client with requirements, a production API, an inherited codebase, and cost/model limits, then is scored by deploying it against held-out simulated users. Across 53 tasks in four domains, the strongest configuration, Claude Opus 5 under Claude Code, passes just 23.9% of evaluation simulations versus an 82.2% expert-authored reference ceiling. Failure modes mirror those of human developers: shallow queries instead of deep record comprehension, almost no client communication, and shipping the first architecture that runs rather than experimenting.

Hugging Face daily papers · 12d agoAI research

The VMs Powering Mobile Agents (Instinct, Claude Code)

A teardown reveals Claude Code runs in Firecracker microVMs with a Rust PID 1 and MITM'd egress, while Instinct rents E2B sandboxes with git-based memory.

The author inspects the virtual machines hosting cloud agents: Claude Code runs in a Firecracker microVM with a custom Rust init (process_api) as PID 1, a 324 MB Bun harness on a read-only disk, and 443-only MITM'd SSE egress to api.anthropic.com with host-rotated OAuth tokens and no inbound access. Instinct rents E2B sandbox-as-a-service Firecracker microVMs (Ubuntu 22.04, 2 vCPU, 1.9 GB RAM) where agent memory is a git repo of Markdown committed by the agent and pushed to S3 as a single bundle, using short-lived STS credentials. Both platforms rely on Firecracker, differing mainly in fleet operator and guest boot configuration.

Hacker News · AI · 8d agoAI tools & infraHN 58↑ · 19 comments1

Bad Likert Judge: A Novel Multi-Turn Technique to Jailbreak LLMs by Misusing Their Evaluation Capability

Unit 42 details the Bad Likert Judge multi-turn jailbreak that abuses LLMs' evaluation capability, raising attack success rates over 60% across six frontier models.

Palo Alto Networks Unit 42 describes the Bad Likert Judge technique, a multi-turn jailbreak that asks a target LLM to act as a Likert-scale judge scoring the harmfulness of example responses. The highest-rated example in each scale can carry harmful content, bypassing the model's internal guardrails. Testing across six state-of-the-art text-generation LLMs showed an average attack success rate increase of more than 60% versus plain attack prompts, with tested models anonymized. The technique targets edge cases rather than typical use, and the article positions the work as guidance for defenders on potential jailbreak risks.

Palo Alto Unit 42 · Aug 17, 2026AI safety & security