Related papers: Stealthy Backdoors as Compression Artifacts
Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), such that the attacked model performs well on benign samples, whereas its prediction will be maliciously changed if the hidden backdoor is activated by the…
Backdoor attacks have emerged as one of the major security threats to deep learning models as they can easily control the model's test-time predictions by pre-injecting a backdoor trigger into the model at training time. While backdoor…
Foundation models have revolutionized computer vision by enabling broad generalization across diverse tasks. Yet, they remain highly susceptible to adversarial perturbations and targeted backdoor attacks. Mitigating such vulnerabilities…
When machine learning training is outsourced to third parties, $backdoor$ $attacks$ become practical as the third party who trains the model may act maliciously to inject hidden behaviors into the otherwise accurate model. Until now, the…
Backdoor attacks change a small portion of training data by introducing hand-crafted triggers and rewiring the corresponding labels towards a desired target class. Training on such data injects a backdoor which causes malicious inference in…
In recent years, there has been an explosive growth in multimodal learning. Image captioning, a classical multimodal task, has demonstrated promising applications and attracted extensive research attention. However, recent studies have…
Deep anomaly detection on sequential data has garnered significant attention due to the wide application scenarios. However, deep learning-based models face a critical security threat - their vulnerability to backdoor attacks. In this…
Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features using the complementary strengths of various data modalities. However, the open nature of such systems inadvertently increases the…
Backdoor attacks are an important type of adversarial threat against deep neural network classifiers, wherein test samples from one or more source classes will be (mis)classified to the attacker's target class when a backdoor pattern is…
Dataset condensation aims to synthesize compact yet informative datasets that retain the training efficacy of full-scale data, offering substantial gains in efficiency. Recent studies reveal that the condensation process can be vulnerable…
Deep neural networks are vulnerable to a range of adversaries. A particularly pernicious class of vulnerabilities are backdoors, where model predictions diverge in the presence of subtle triggers in inputs. An attacker can implant a…
Deep neural networks are vulnerable to backdoor attacks, a type of adversarial attack that poisons the training data to manipulate the behavior of models trained on such data. Clean-label attacks are a more stealthy form of backdoor attacks…
Backdoor attacks have severely threatened deep neural network (DNN) models in the past several years. These attacks can occur in almost every stage of the deep learning pipeline. Although the attacked model behaves normally on benign…
The various post-processing methods for deep-learning-based models, such as quantification, pruning, and fine-tuning, play an increasingly important role in artificial intelligence technology, with pre-train large models as one of the main…
Deep learning models have recently shown to be vulnerable to backdoor poisoning, an insidious attack where the victim model predicts clean images correctly but classifies the same images as the target class when a trigger poison pattern is…
We introduce a new attack paradigm that embeds hidden adversarial capabilities directly into diffusion models via fine-tuning, without altering their observable behavior or requiring modifications during inference. Unlike prior approaches…
Backdoor attack intends to inject hidden backdoor into the deep neural networks (DNNs), such that the prediction of infected models will be maliciously changed if the hidden backdoor is activated by the attacker-defined trigger. Currently,…
We investigate a new method for injecting backdoors into machine learning models, based on compromising the loss-value computation in the model-training code. We use it to demonstrate new classes of backdoors strictly more powerful than…
Over the past decade, side-channels have proven to be significant and practical threats to modern computing systems. Recent attacks have all exploited the underlying shared hardware. While practical, mounting such a complicated attack is…
Knowledge Distillation (KD) is essential for compressing large models, yet relying on pre-trained "teacher" models downloaded from third-party repositories introduces serious security risks--most notably backdoor attacks. Existing KD…