DEFUSE: Generalizable Backdoor Defense for Self-Supervised Encoders with Generative Priors
Self-supervised learning (SSL) encoders are vulnerable to backdoor attacks, posing threats to both visual SSL encoders and vision-language encoders. Existing defenses are typically designed for only one of these paradigms and rely on restrictive assumptions such as access to uninfected in-distribution data or precomputed pseudo-labels, which are difficult to satisfy in practice. To address these limitations, we propose DEFUSE, a generalizable backdoor detection framework for SSL encoders. Inspired by Bayesian posterior inference, we reformulate backdoor detection as a representation-conditione
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 46%Open-sourcing a two-stage prompt-injection detector (regex gate + quantised DeBERTa-v3 ONNX), trained partly on real attacks from a game I ran [P] →
- FuzzySimilar title/name (fuzzy) · 84%GoogleCloudPlatform/generative-ai →
“Fuzzy title match (0.92): “DEFUSE: Generalizable Backdoor Defense for Self-Supervised E” ≈ “GoogleCloudPlatform/generative-ai””
- FuzzyOverlapping authors or contributors · 62%modular/modular →
“Shared author/contributor keys: liu”
- FuzzySimilar title/name (fuzzy) · 59%steven2358/awesome-generative-ai →
“Fuzzy title match (0.73): “DEFUSE: Generalizable Backdoor Defense for Self-Supervised E” ≈ “steven2358/awesome-generative-ai””
- LinkedLinked via arxiv author · 85%Tuo Chen →
“DEFUSE: Generalizable Backdoor Defense for Self-Supervised Encoders with Generative Priors”
- LinkedLinked via arxiv author · 85%Jie Gui →
“DEFUSE: Generalizable Backdoor Defense for Self-Supervised Encoders with Generative Priors”
- LinkedLinked via arxiv author · 85%Minjing Dong →
“DEFUSE: Generalizable Backdoor Defense for Self-Supervised Encoders with Generative Priors”
- LinkedLinked via arxiv author · 85%Lanting Fang →
“DEFUSE: Generalizable Backdoor Defense for Self-Supervised Encoders with Generative Priors”