Related papers: When Attention Betrays: Erasing Backdoor Attacks i…
Vision-Language-Action (VLA) models are widely deployed in safety-critical embodied AI applications such as robotics. However, their complex multimodal interactions also expose new security vulnerabilities. In this paper, we investigate a…
Vision-Language-Action (VLA) models have advanced robotic control by enabling end-to-end decision-making directly from multimodal inputs. However, their tightly coupled architectures expose novel security vulnerabilities. Unlike traditional…
Vision-Language-Action (VLA) models map multimodal perception and language instructions to executable robot actions, making them particularly vulnerable to behavioral backdoor manipulation: a hidden trigger introduced during training can…
Recent advances in vision-language-action (VLA) models have greatly improved embodied AI, enabling robots to follow natural language instructions and perform diverse tasks. However, their reliance on uncurated training datasets raises…
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…
Supervised fine-tuning has become the predominant method for adapting large pretrained models to downstream tasks. However, recent studies have revealed that these models are vulnerable to backdoor attacks, where even a small number of…
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…
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…
Despite the strong multimodal performance, large vision-language models (LVLMs) are vulnerable during fine-tuning to backdoor attacks, where adversaries insert trigger-embedded samples into the training data to implant behaviors that can be…
Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a…
Fine-tuned Large Language Models (LLMs) are vulnerable to backdoor attacks through data poisoning, yet the internal mechanisms governing these attacks remain a black box. Previous research on interpretability for LLM safety tends to focus…
Low-Rank Adaptation (LoRA) has emerged as an efficient method for fine-tuning large language models (LLMs) and is widely adopted within the open-source community. However, the decentralized dissemination of LoRA adapters through platforms…
Recent studies have revealed that \textit{Backdoor Attacks} can threaten the safety of natural language processing (NLP) models. Investigating the strategies of backdoor attacks will help to understand the model's vulnerability. Most…
Vision transformers have achieved impressive performance in various vision-related tasks, but their vulnerability to backdoor attacks is under-explored. A handful of existing works focus on dirty-label attacks with wrongly-labeled poisoned…
Vision Language Models (VLMs) have shown remarkable performance, but are also vulnerable to backdoor attacks whereby the adversary can manipulate the model's outputs through hidden triggers. Prior attacks primarily rely on single-modality…
Backdoor attack has emerged as a novel and concerning threat to AI security. These attacks involve the training of Deep Neural Network (DNN) on datasets that contain hidden trigger patterns. Although the poisoned model behaves normally on…
Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of unsafe behaviors while evading detection during normal interactions. The high dimensionality of potential triggers in the token space and the diverse…
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),…
Backdoor attacks can cause reinforcement learning (RL) policies to behave normally under clean inputs while executing malicious behaviors when triggers are present. Existing RL backdoor attacks are primarily studied in simulation and often…
Backdoored and privacy-leaking deep neural networks pose a serious threat to the deployment of machine learning systems in security-critical settings. Existing defenses for backdoor detection and membership inference typically require…