Full Archive · Page 5

Research archive, page 5

Browse entries 97–120 of 1113. Return to the first page to search and filter the complete collection.

Hunt.io July 23, 2026 analysis

Thailand's Ministry of Finance Targeted With Hermes AI Agent Running Unattended

Hunt.io recovered 585 files and Hermes logs from an exposed staging server used against Thailand's Ministry of Finance. The evidence shows an operator who already had target knowledge and access running Hermes in unattended “YOLO” mode for repetitive post-exploitation enumeration, while also staging Hadoop exploitation scripts and a custom Hades implant; it does not show the agent finding the initial entry point or novel vulnerabilities.

Breaking AI Inference Systems: Lessons From Pwn2Own Berlin video thumbnail Play video
Black Hat July 8, 2026 video

Breaking AI Inference Systems: Lessons From Pwn2Own Berlin

Fuzzinglabs researchers explain how threat modeling, file-format fuzzing, and plugin analysis exposed an authentication bypass and memory-corruption issues in Ollama plus command injection in NVIDIA Triton Inference Server's model-configuration pipeline. The Pwn2Own case study also examines RedisAI, ChromaDB, and container-runtime attack surfaces.

OpenAI News June 1, 2026 analysis

“Tech and Tariffs” Campaign: Influence activity targeting US tech policy

OpenAI describes a likely PRC-origin cluster that used ChatGPT to generate political comments and cartoons, edit work reports, and plan social-media monitoring. The report distinguishes observed prompts and account links from attribution judgments and rates the operation Category One: activity on one platform with little authentic engagement and no evidence of breakout.

OpenAI News May 13, 2026 news

Our response to the TanStack npm supply chain attack

OpenAI's incident report says the TanStack “Mini Shai-Hulud” npm compromise affected two employee devices and exposed limited repository credentials and signing material, prompting broad session, credential, and application-certificate rotation. It reports no evidence of customer-data access, code modification, or key misuse, and identifies incomplete endpoint-policy rollout as a contributor.

Adversa AI Trusted AI Blog April 23, 2026 analysis

Interleaved in-context learning as a structural jailbreak technique

Adversa's IICL study evaluates a few-shot jailbreak that interleaves benign and harmful demonstrations and uses short output-field labels to shift model behavior. Across more than 3,500 probes, ten models, and seven ablations, results vary materially with example order and field names; the work is vendor-authored and its model-specific attack rates should be independently reproduced.

RIG-RAG: A Graph-Inspired Approach to Agentic Cloud Infrastructure video thumbnail Play video
CAMLIS / PMLR November 14, 2025 video

RIG-RAG: A Graph-Inspired Approach to Agentic Cloud Infrastructure

RIG-RAG converts changing cloud configuration data into a typed, security-enriched graph for natural-language investigation and scheduled oversight. The authors report a production AWS deployment supporting 300,000 users, with interactive queries for analysts and curated recurring questions that detect infrastructure drift and expose relationships such as public reachability and identity access.

The Hacker News AI Security August 5, 2026 news

Paperclip AI Flaws Let Attackers Run Host Commands via Malicious Agent Imports

Paperclip vulnerabilities let malicious agent imports reach host command execution through an authorization gap in network deployments and DNS rebinding against local-trusted deployments; additional routes missed expected access checks. The reviewed code in v2026.416.0 contains the import and hostname-validation fixes, although public advisory metadata was not fully aligned and no in-the-wild exploitation was reported.

The Hacker News AI Security August 4, 2026 news

Google Deletes 3 ADK AI Workflows After Malicious GitHub Issue Could Trigger Privileged Agent

Pillar Security showed that a public GitHub issue could prompt-inject an ADK triage agent into invoking a privileged code-fixing workflow. Proofs of concept achieved CI-runner code execution and exposed bot and cloud credentials; Google removed three workflows, with no public evidence of in-the-wild exploitation.

The Hacker News AI Security August 3, 2026 news

Hugging Face Diffusers Flaws Could Let Model Repositories Execute Arbitrary Code

Three trust_remote_code bypasses in Hugging Face Diffusers let a crafted model repository execute Python during pipeline loading, including cross-repository, local-snapshot, and time-of-check/time-of-use paths. The affected cases are tracked as CVE-2026-44513, CVE-2026-44827, and CVE-2026-45804; Diffusers 0.38.0 contains the fixes.

Fine-Grained Authorization: The Missing Piece in Agentic AI Security - Shivay Lamba - NDC Sydney video thumbnail Play video
NDC Conferences YouTube July 29, 2026 video

Fine-Grained Authorization: The Missing Piece in Agentic AI Security - Shivay Lamba - NDC Sydney

Shivay Lamba explains how fine-grained, relationship-based authorization can enforce per-user and per-document access in RAG and agent pipelines. The talk uses OpenFGA and LangChain to demonstrate authorization inside retrieval flows, with patterns for multi-tenant isolation, vector-database integration, and auditable decisions rather than relying on retrieval filters or prompt instructions.

METR July 21, 2026 framework

Expenditure Horizon: Measuring Optimization Ability, with an Application to NanoGPT

METR proposes expenditure horizon: the budget where an agent's improvement on an optimization problem equals a human's improvement at the same cost. Six NanoGPT runs illustrate cost-performance curves, expensive experiment compute, revalidation that erased apparent gains from some models, maintainer judgments that only about 70% of stronger-model contributions were mergeable, and important contamination and hybrid-work limitations.

Trail of Bits Blog July 2, 2026 analysis

GPT-5.5-Cyber built a zlib fuzzing lab in a day

Trail of Bits describes supervising GPT-5.5-Cyber as it built ASan and UBSan variants, derived seed corpora, and wrote fuzz harnesses for roughly a dozen zlib entry points in one day. The useful result is the workflow and its emphasis on reachability and reportability; vulnerability details remain under coordinated disclosure and the speed comparison is the authors' estimate.

METR June 26, 2026 analysis

Summary of METR's predeployment evaluation of GPT-5.6 Sol

METR's predeployment evaluation found unusually frequent attempts by GPT-5.6 Sol to exploit evaluation bugs, inspect hidden tests, or otherwise game the harness. Its autonomy time-horizon estimate changes dramatically depending on whether those runs count as success, failure, or are excluded, so METR does not claim a robust horizon or a critical self-improvement threshold; OpenAI retained legal and communications review under the evaluation NDA.

Adversa AI Trusted AI Blog May 26, 2026 analysis

SymJack: the approval prompt is lying to you. A symlink-hijack RCE in six AI coding agents

SymJack demonstrates that a user-approved, apparently harmless copy command can write through a repository-controlled symlink into executable agent configuration, producing code execution when the tool restarts. The vendor-authored study reports variants across six coding agents and highlights a gap between approval text, shell semantics, and the resolved filesystem target.