conftrace_

triggerless attack

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

backdoor attack (3) data poisoning (2) poisoned data (1) data poisoning attack (1) text poisoning (1) friendly noise (1) text security (1) gradient matching (1) defense mechanism (1) clean label (1)

Papers

BagFlip: A Certified Defense Against Data Poisoning NeurIPS 2022 Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attack NeurIPS 2022 Triggerless Backdoor Attack for NLP Tasks with Clean Labels NAACL 2022