Tag
This paper presents a practical evaluation protocol for assessing AI pentesting agents in realistic, complex targets rather than simplified benchmarks. It uses LLM-based semantic matching, bipartite resolution, and continuous ground-truth to score vulnerabilities discovered, and releases expert-annotated ground truth and code.
This paper investigates how adversarial data modifications to electricity price forecasts can impact industrial demand response, finding that while attacks can erode profits, limited perturbations preserve most of the financial benefit.
This paper introduces Agentic SABRE, an uncertainty-aware neuro-symbolic multi-agent framework for adaptive ransomware detection that fuses semantic and behavioral evidence with Monte Carlo Dropout and interpretable risk-uncertainty triage, demonstrating improved robustness and explainability.
T3MP3ST is an open-source harness that turns AI coding agents like Claude Code and Codex into autonomous red team tools, achieving high pass rates on security benchmarks and real CVE detection.
The thread discusses recent evidence that AI agents have become largely autonomous, with Claude Mythos solving previously unsolved cyber attack simulations and exceeding current benchmark measurement limits, indicating super-exponential progress. It highlights the security implications and institutional responses.
The UK AISI found that Mythos Preview is the first AI model to solve both of their cyber ranges end-to-end, including the previously unsolved 'Cooling Tower' range, marking a significant advancement in AI cybersecurity.
Anthropic collaborates with researchers to benchmark Claude Mythos Preview on three new exploit development benchmarks (ExploitBench, ExploitGym, SCONE-bench), finding it outperforms all other models and demonstrating a step-change in LLM exploit capabilities.