cyber-security

Tag

Cards List
#cyber-security

From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World

Hugging Face Daily Papers · 3d ago Cached

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.

0 favorites 0 likes
#cyber-security

Does Demand Response Increase Vulnerability to Cyber Attacks by Adversarial Data Modifications?

arXiv cs.LG · 2026-07-09 Cached

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.

0 favorites 0 likes
#cyber-security

Agentic SABRE: An Uncertainty-Aware Neuro-Symbolic Multi-Agent Framework for Adaptive Ransomware Detection

arXiv cs.AI · 2026-07-07 Cached

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.

0 favorites 0 likes
#cyber-security

@elder_plinius: INTRODUCING: T3MP3ST!!! AUTONOMOUS HACKBOT STRIKE FORCE BRING THE STORM your favorite coding agent is now a full-stack …

X AI KOLs Timeline · 2026-07-05 Cached

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.

0 favorites 0 likes
#cyber-security

@daniel_mac8: https://x.com/daniel_mac8/status/2054994899422826592

X AI KOLs Following · 2026-05-14 Cached

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.

0 favorites 0 likes
#cyber-security

@bcherny: The UK AISI found Mythos Preview is the first model to solve both their cyber ranges end-to-end. No model had ever solv…

X AI KOLs Following · 2026-05-13 Cached

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.

0 favorites 0 likes
#cyber-security

May 22, 2026Frontier Red TeamMeasuring LLMs’ ability to develop exploits

Anthropic Research · 2026-06-17 Cached

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.

0 favorites 0 likes
← Back to home

Submit Feedback