REVIEW 9 cited by
Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks
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
read the original abstract
Deep neural networks (DNNs) are known vulnerable to backdoor attacks, a training time attack that injects a trigger pattern into a small proportion of training data so as to control the model's prediction at the test time. Backdoor attacks are notably dangerous since they do not affect the model's performance on clean examples, yet can fool the model to make incorrect prediction whenever the trigger pattern appears during testing. In this paper, we propose a novel defense framework Neural Attention Distillation (NAD) to erase backdoor triggers from backdoored DNNs. NAD utilizes a teacher network to guide the finetuning of the backdoored student network on a small clean subset of data such that the intermediate-layer attention of the student network aligns with that of the teacher network. The teacher network can be obtained by an independent finetuning process on the same clean subset. We empirically show, against 6 state-of-the-art backdoor attacks, NAD can effectively erase the backdoor triggers using only 5\% clean training data without causing obvious performance degradation on clean examples. Code is available in https://github.com/bboylyg/NAD.
Forward citations
Cited by 9 Pith papers
-
Lethe: Purifying Backdoored Large Language Models with Knowledge Dilution
LETHE uses parameter-level model merging plus prompt-level word definitions to dilute backdoor behavior in LLMs, cutting attack success to below 7% in most tested settings.
-
BURN: Backdoor Unlearning via Adversarial Boundary Analysis
BURN removes backdoors from trained models by detecting poison samples through adversarial boundary distance and re-labeling them with labels recovered by adversarial perturbations.
-
Circumventing Backdoor Space via Weight Symmetry
A weight-permutation-based two-stage mode connectivity method purifies backdoored neural networks across supervised and self-supervised learning with few clean samples.
-
BadSR: Stealthy Label Backdoor Attacks on Image Super-Resolution
BadSR creates stealthy poisoned high-resolution labels for super-resolution backdoors, achieving above 80% attack success across five SR models while keeping labels visually close to clean images.
-
Defense Against LLM Backdoors using Critical Neuron Isolation Pruning
A trigger-inversion plus activation-difference pruning pipeline removes LLM backdoors with ~0.1% neuron intervention and >95% relative ASR reduction.
-
From Detection to Correction: Backdoor-Resilient Face Recognition via Vision-Language Trigger Detection and Noise-Based Neutralization
A majority vote of large vision-language models is claimed to detect backdoor triggers in face images, with calibrated noise correcting poisoned samples at 100% accuracy.
-
NT-ML: Backdoor Defense via Non-target Label Training and Mutual Learning
NT-ML combines non-target label training and mutual learning to purify a backdoored model using a small set of clean samples.
-
Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies
The paper proposes a one-to-one mapping between six causes of distribution shift and several AI safety issues, arguing for mutual method transfer through aligned definitions.
-
A Robust Attack: Displacement Backdoor Attack
Displacement Backdoor Attack blends shifted self-copies of an image into the original as a backdoor trigger and reportedly maintains high attack success under data augmentation.
Discussion (0). Continue with ORCID to comment.