Provably effective detection of effective data poisoning attacks
On the map: LLM safety and security → Backdoor and data poisoning attacks
Abstract (arXiv)
This paper establishes a mathematically precise definition of dataset poisoning attack and proves that the very act of effectively poisoning a dataset ensures that the attack can be effectively detected. On top of a mathematical guarantee that dataset poisoning is identifiable by a new statistical test that we call the Conformal Separability Test, we provide experimental evidence that we can adequately detect poisoning attempts in the real world.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security. First posted on arXiv 21 Jan 2025.
Builds on
0 of 0 references.
No references here yet.
Built on by
Not cited yet.