backdoor attacks 1black-box attacks 1data poisoning 1representation alignment 1trigger generalization 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.CR2026
Lilith: Backdoor Generalization under Training-Inference Trigger Shift
Zhou Feng, Jiahao Chen, Chunyi Zhou +6
The paper studies how backdoor attacks can remain effective when the trigger used at inference time differs from the one seen during training, and proposes Lilith, a black‑box meth…
cs.CR2026
Shattering the Echo Chamber: Hidden Safeguards in Manuscripts Against the AI Takeover of Peer Review
Oubo Ma, Ruixiao Lin, Jiahao Chen +3
As LLMs become increasingly capable, editorial boards and program committees are growing concerned about reviewers who fully outsource peer review to commercial chatbots. This conc…