https://github.com/ChenWu98/agent-attack
[Arxiv 2024] Adversarial attacks on multimodal agents
https://github.com/ChenWu98/agent-attack
adversarial-attacks agent llm multimodal safety
Last synced: 3 months ago
JSON representation
[Arxiv 2024] Adversarial attacks on multimodal agents
- Host: GitHub
- URL: https://github.com/ChenWu98/agent-attack
- Owner: ChenWu98
- License: mit
- Created: 2024-06-19T01:34:17.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-06-28T20:04:00.000Z (over 1 year ago)
- Last Synced: 2024-08-12T08:13:10.295Z (about 1 year ago)
- Topics: adversarial-attacks, agent, llm, multimodal, safety
- Language: Python
- Homepage: https://chenwu.io/attack-agent/
- Size: 702 MB
- Stars: 28
- Watchers: 1
- Forks: 3
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- Awesome-MLLM-Safety - Github - attack.svg?style=social&label=Star) (Attack)
- awesome-llm-agent-security - Agent-Attack - Attack vectors<br>- Defense evaluation<br>- Risk assessment | (📚 Research & Publications / 🔒 OWASP Top 10 for AI Agents (Non official))
- awesome-llm-agent-security - Agent-Attack - Attack vectors<br>- Defense evaluation<br>- Risk assessment | (📚 Research & Publications / 🔒 OWASP Top 10 for AI Agents (Non official))