Building a Benchmark for Decomposition Attacks for Agents at AI Safety Night
chhaviyadav_ · x · 2026-08-19
The author is giving a talk at the AI Safety Night organized by Intel, presenting their latest work on building a benchmark for Decomposition Attacks for Agents. The session will detail the approach to evaluating security vulnerabilities in AI agent systems.
More from Safety
- Researchers find AI agents can infect each other with self-propagating 'mind viruses' — Polymarket · 2026-08-19
- Google Reveals AVDH: Agentic Framework for Automated Vulnerability Discovery — rseroter · 2026-08-19
- Security Concerns Over Google Moving A2A Under Agentic AI — CackleRooster · 2026-08-19
- Why "pause AI for 6 months" never made sense: no consensus on the problem — soumitrashukla9 · 2026-08-19
- Researcher calls Irregular "not a serious firm," urges OpenAI and Meta probes — nptacek · 2026-08-19
- Zvi comments on 'user-centric AI': rejecting corporate ideological imposition — TheZvi · 2026-08-19