The authors construct a probe by editing a selected MLP layer of CLIP in closed form.
Repurposing backdoor trigger mechanisms as probes for adversarial defense in CLIP models
BaP achieves robust accuracy improvements from 1.0% to 52.3% across 16 benchmarks while retaining clean accuracy
Research Lab
Zhongqi Wang · Jie Zhang · Nie Sen · Zhiyu Chen · Shiguang Shan · Xilin Chen
Xuzhou University of Technology · Chinese Academy of Sciences · University of Chinese Academy of Sciences
Research Digest··2 min read
Wang et al.
Why this paper
From Chinese Academy of Sciences and 2 others
In one line
Repurposing adversarial activation shifts as backdoor probes defends CLIP against attacks at test time without retraining.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§