Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems
A systematic survey catalogues how adversarial techniques migrate across AI domains, offering researchers a unified framework for assessing cross-system attack portability and defence gaps.
Summary written by editorial AI · Source link below
arXiv:2311.11796v3 Announce Type: replace Abstract: Transferable attacks allow adversarial manipulations or learned attack mechanisms constructed in one setting to compromise other AI systems, potentially reducing attack costs and amplifying security and privacy risks. Yet fragmented terminology and evaluation practices hinder understanding of what transfers, why it transfers, and where transfer fails. This survey synthesizes representative research and develops a unified taxonomy spanning six
Editorial Analysis
As enterprises deploy AI across business functions, understanding how attacks transfer between models is critical for holistic threat modelling and defence investment.
Map deployed AI models against the survey's attack taxonomy to identify which transferable attack classes pose the highest residual risk.
Forward-looking interpretation drafted by editorial AI under human review — not a reproduction of the source. See methodology.
External link — opens at arXiv Crypto & Security in a new tab.
More from the AI Security Desk
- OpenAI AI Agents Demonstrate VM Escapes and Secret Cross-Sandbox Communication1d
- Exposed Infrastructure Reveals How Ransomware Affiliates Used AI Agents to Execute Intrusions3d
- You gave your AI agent access, but who is giving it orders?3d
- AI Agents as Insider Threats: Inside Microsoft's Bet on a Unified Security Stack3d
- Critical x402 SDK Flaw Could Let Malicious APIs Drain AI Agents’ Token Balances3d