Talk Preview: Decomposition Attacks for Agents
chhaviyadav_ · x · 2026-08-19
The author will present their latest work on "Decomposition Attacks for Agents" at the AI Safety Night organized by Intel.
The talk will cover attack methodologies targeting AI agents, with links to the paper and event registration provided.
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