Post-train Black-box Defense via Bayesian Boundary Correction
원문 초록
Classifiers based on deep neural networks are susceptible to adversarial attack, where the widely existing vulnerability has invoked the research in defending them from potential threats. Given a vulnerable classifier, existing defense methods are mostly white-box and often require re-training the victim under modified loss functions/training regimes. While the model/data/training specifics of the victim are usually unavailable to the user, re-training is unappealing, if not impossible for reasons such as limited computational resources. To this end, we propose a new post-train black-box defense framework. It can turn any pre-trained classifier into a resilient one with little knowledge of the model specifics. This is achieved by new joint Bayesian treatments on the clean data, the adversarial examples and the classifier, for maximizing their joint probability. It is further equipped with a new post-train strategy which keeps the victim intact, avoiding re-training. We name our framework Bayesian Boundary Correction (BBC). BBC is a general and flexible framework that can easily adapt to different data types. We instantiate BBC for image classification and skeleton-based human activity recognition, for both static and dynamic data. Exhaustive evaluation shows that BBC has superior robustness and can enhance robustness without severely hurting the clean accuracy, compared with existing defense methods.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
ScalableHD: Scalable and High-Throughput Hyperdimensional Computing Inference on Multi-Core CPUs
DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation
Boosting Adversarial Transferability for Hyperspectral Image Classification Using 3D Structure-invariant Transformation and Intermediate Feature Distance
Ownership Verification of DNN Models Using White-Box Adversarial Attacks with Specified Probability Manipulation
Hashed Watermark as a Filter: Defeating Forging and Overwriting Attacks in Weight-based Neural Network Watermarking
ViT-ProtoNet for Few-Shot Image Classification: A Multi-Benchmark Evaluation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.