Related papers: GUARD:Dual-Agent based Backdoor Defense on Chain-o…

Multi-agent systems leverage advanced AI models as autonomous agents that interact, cooperate, or compete to complete complex tasks across applications such as robotics and traffic management. Despite their growing importance, safety in…

Backdoor attack is a powerful attack algorithm to deep learning model. Recently, GNN's vulnerability to backdoor attack has been proved especially on graph classification task. In this paper, we propose the first backdoor detection and…

Backdoor (trojan) attacks embed hidden, controllable behaviors into machine-learning models so that models behave normally on benign inputs but produce attacker-chosen outputs when a trigger is present. This survey reviews the rapidly…

While Chain-of-Thought (CoT) prompting has become a standard paradigm for eliciting complex reasoning capabilities in Large Language Models, it inadvertently exposes a new attack surface for backdoor attacks. Existing CoT backdoor attacks…

Retrieval-Augmented Code Generation (RACG) is increasingly adopted to enhance Large Language Models for software development, yet its security implications remain dangerously underexplored. This paper conducts the first systematic…

Automatic generation of computer-aided design (CAD) models is a core technology for enabling intelligence in advanced manufacturing. Existing generation methods based on large language models (LLMs) often fall short when handling complex…

Retrieval-augmented generation (RAG) enhances factual grounding by integrating retrieval mechanisms with generative models but introduces new attack surfaces, particularly through backdoor attacks. While prior research has largely focused…

Backdoor attacks (BAs) are an emerging threat to deep neural network classifiers. A victim classifier will predict to an attacker-desired target class whenever a test sample is embedded with the same backdoor pattern (BP) that was used to…

Backdoor attacks have become a major security threat for deploying machine learning models in security-critical applications. Existing research endeavors have proposed many defenses against backdoor attacks. Despite demonstrating certain…

Object detection models, widely used in security-critical applications, are vulnerable to backdoor attacks that cause targeted misclassifications when triggered by specific patterns. Existing backdoor defense techniques, primarily designed…

Generative code models (GCMs) significantly enhance development efficiency through automated code generation and code summarization. However, building and training these models require computational resources and time, necessitating…

Adversarial attacks against deep learning models represent a major threat to the security and reliability of natural language processing (NLP) systems. In this paper, we propose a modification to the BERT-Attack framework, integrating…

While generative retrieval (GR) demonstrates competitive performance on standard retrieval benchmarks, existing approaches directly map queries to document identifiers (docids) without intermediate deliberation, limiting their effectiveness…

Deep Neural Networks (DNNs) have recently achieved great success in many tasks, which encourages DNNs to be widely used as a machine learning service in model sharing scenarios. However, attackers can easily generate adversarial examples…

Predicting and classifying faults in electricity networks is crucial for uninterrupted provision and keeping maintenance costs at a minimum. Thanks to the advancements in the field provided by the smart grid, several data-driven approaches…

Backdoor attacks on deep learning represent a recent threat that has gained significant attention in the research community. Backdoor defenses are mainly based on backdoor inversion, which has been shown to be generic, model-agnostic, and…

The proliferation of open-source software (OSS) has made software supply chains prime targets for attacks like Package Confusion, where adversaries publish malicious packages with names deceptively similar to legitimate ones. To protect…

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 have posed a significant threat to the security of deep neural networks (DNNs). Despite considerable strides in developing defenses against backdoor attacks in the visual domain, the specialized defenses for the audio…

The deployment of Large Reasoning Models (LRMs) in high-stakes decision-making pipelines has introduced a novel and opaque attack surface: reasoning backdoors. In these attacks, the model's intermediate Chain-of-Thought (CoT) is manipulated…