相关论文: BadVim: Unveiling Backdoor Threats in Visual State…

Backdoor attacks compromise model reliability by using triggers to manipulate outputs. Trigger inversion can accurately locate these triggers via a generator and is therefore critical for backdoor defense. However, the discrete nature of…

Backdoor data poisoning is an emerging form of adversarial attack usually against deep neural network image classifiers. The attacker poisons the training set with a relatively small set of images from one (or several) source class(es),…

Deep neural networks have been shown to be vulnerable to backdoor attacks, which could be easily introduced to the training set prior to model training. Recent work has focused on investigating backdoor attacks on natural images or toy…

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across various tasks, yet they remain vulnerable to backdoor attacks. Existing defense methods predominantly focus on sample-level defense, which relies on the…

The challenge of WAD (web attack detection) is growing as hackers continuously refine their methods to evade traditional detection. Deep learning models excel in handling complex unknown attacks due to their strong generalization and…

Vision-Language Models (VLMs), with their strong reasoning and planning capabilities, are widely used in embodied decision-making (EDM) tasks in embodied agents, such as autonomous driving and robotic manipulation. Recent research has…

With the thriving of deep learning and the widespread practice of using pre-trained networks, backdoor attacks have become an increasing security threat drawing many research interests in recent years. A third-party model can be poisoned in…

Deep neural networks (DNN), despite their remarkable performance, are highly vulnerable to backdoor attacks. Existing defenses mainly rely on activation anomaly analysis or trigger reverse engineering and often require clean samples or…

Recent researches have shown that Large Language Models (LLMs) are susceptible to a security threat known as Backdoor Attack. The backdoored model will behave well in normal cases but exhibit malicious behaviours on inputs inserted with a…

Backdoor attacks, in which a model behaves maliciously when given an attacker-specified trigger, pose a major security risk for practitioners who depend on publicly released language models. As a countermeasure, backdoor detection methods…

The emergence of Vision-Language Models (VLMs) represents a significant advancement in integrating computer vision with Large Language Models (LLMs) to generate detailed text descriptions from visual inputs. Despite their growing…

Vision-Language-Action (VLA) models have become foundational to modern embodied AI systems. By integrating visual perception, language understanding, and action planning, they enable general-purpose task execution across diverse…

Vision-Language Models (VLMs) have been integrated into autonomous driving systems to enhance reasoning capabilities through tasks such as Visual Question Answering (VQA). However, the robustness of these systems against backdoor attacks…

The advent of clinical language models integrated into electronic health records (EHR) for clinical decision support has marked a significant advancement, leveraging the depth of clinical notes for improved decision-making. Despite their…

Over the past few years, the emergence of backdoor attacks has presented significant challenges to deep learning systems, allowing attackers to insert backdoors into neural networks. When data with a trigger is processed by a backdoor…

Semantic communication systems, which leverage Generative AI (GAI) to transmit semantic meaning rather than raw data, are poised to revolutionize modern communications. However, they are vulnerable to backdoor attacks, a type of poisoning…

Backdoor attacks pose a critical threat to the security of deep neural networks, yet existing efforts on universal backdoors often rely on visually salient patterns, making them easier to detect and less practical at scale. In this work, we…

Federated Learning (FL) allows multiple clients to collaboratively train a Neural Network (NN) model on their private data without revealing the data. Recently, several targeted poisoning attacks against FL have been introduced. These…

Code LLMs are increasingly employed in software development. However, studies have shown that they are vulnerable to backdoor attacks: when a trigger (a specific input pattern) appears in the input, the backdoor will be activated and cause…

Backdoor attacks embed hidden malicious behaviors into deep learning models, which only activate and cause misclassifications on model inputs containing a specific trigger. Existing works on backdoor attacks and defenses, however, mostly…