REVIEW 5 cited by
Adversarial Backdoor Defense in CLIP
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Adversarial Backdoor Defense in CLIP
read the original abstract
Multimodal contrastive pretraining, exemplified by models like CLIP, has been found to be vulnerable to backdoor attacks. While current backdoor defense methods primarily employ conventional data augmentation to create augmented samples aimed at feature alignment, these methods fail to capture the distinct features of backdoor samples, resulting in suboptimal defense performance. Observations reveal that adversarial examples and backdoor samples exhibit similarities in the feature space within the compromised models. Building on this insight, we propose Adversarial Backdoor Defense (ABD), a novel data augmentation strategy that aligns features with meticulously crafted adversarial examples. This approach effectively disrupts the backdoor association. Our experiments demonstrate that ABD provides robust defense against both traditional uni-modal and multimodal backdoor attacks targeting CLIP. Compared to the current state-of-the-art defense method, CleanCLIP, ABD reduces the attack success rate by 8.66% for BadNet, 10.52% for Blended, and 53.64% for BadCLIP, while maintaining a minimal average decrease of just 1.73% in clean accuracy.
Forward citations
Cited by 5 Pith papers
-
TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting
TimeGuard defends time series forecasting against backdoors via channel-wise pool training initialized by time-aware criteria and expanded with distance-regularized loss selection, improving poisoned MAE by 1.96x whil...
-
Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP
PAR fine-tunes CLIP to remove backdoors from structured triggers while preserving standard performance, and works even with only synthetic image-text pairs.
-
TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting
TimeGuard employs channel-wise pool training initialized with time-aware criteria and distance-regularized loss selection to defend time series forecasting against backdoor attacks, improving robustness by 1.96x while...
-
TokenSwap: Backdoor Attack on the Compositional Understanding of Large Vision-Language Models
TokenSwap poisons LVLMs so that triggered images produce captions with subject and object roles reversed, achieving high attack success while evading a perplexity-based detector.
-
A Patch-based Cross-view Regularized Framework for Backdoor Defense in Multimodal Large Language Models
A patch-augmented cross-view regularization method reduces backdoor attack success rates in multimodal LLMs by enforcing output differences between original and perturbed views while using entropy constraints to prese...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.