Related papers: BadToken: Token-level Backdoor Attacks to Multi-mo…
The security concerns surrounding Large Language Models (LLMs) have been extensively explored, yet the safety of Multimodal Large Language Models (MLLMs) remains understudied. In this paper, we observe that Multimodal Large Language Models…
Large Language Models (LLMs) have shown significant promise in real-world decision-making tasks for embodied artificial intelligence, especially when fine-tuned to leverage their inherent common sense and reasoning abilities while being…
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…
The rapid progress of Large Language Models (LLMs) has opened up new opportunities across various domains and applications; yet it also presents challenges related to potential misuse. To mitigate such risks, red teaming has been employed…
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…
The increasing demand for customized Large Language Models (LLMs) has led to the development of solutions like GPTs. These solutions facilitate tailored LLM creation via natural language prompts without coding. However, the trustworthiness…
In recent years, deep learning-based Monocular Depth Estimation (MDE) models have been widely applied in fields such as autonomous driving and robotics. However, their vulnerability to backdoor attacks remains unexplored. To fill the gap in…
With the rapid rise of personalized AI, customized large language models (LLMs) equipped with Chain of Thought (COT) reasoning now power millions of AI agents. However, their complex reasoning processes introduce new and largely unexplored…
When large language model (LLM) systems interact with external data to perform complex tasks, a new attack, namely prompt injection, becomes a significant threat. By injecting instructions into the data accessed by the system, the attacker…
Multivariate long-term time series forecasting (MLTSF) models are increasingly deployed in critical domains such as climate, finance, and transportation. Despite their growing importance, the security of MLTSF models against backdoor…
Autoregressive Visual Language Models (VLMs) showcase impressive few-shot learning capabilities in a multimodal context. Recently, multimodal instruction tuning has been proposed to further enhance instruction-following abilities. However,…
Large language models (LLMs) have raised concerns about potential security threats despite performing significantly in Natural Language Processing (NLP). Backdoor attacks initially verified that LLM is doing substantial harm at all stages,…
The rapid development of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) has exposed vulnerabilities to various adversarial attacks. This paper provides a comprehensive overview of jailbreaking research targeting…
Backdoor attacks pose an important security threat to textual large language models. Exploring textual backdoor attacks not only helps reveal the potential security risks of models, but also promotes innovation and development of defense…
The integration of Large Language Models (LLMs) into healthcare applications offers promising advancements in medical diagnostics, treatment recommendations, and patient care. However, the susceptibility of LLMs to adversarial attacks poses…
Masked diffusion language models (MDLMs) are emerging as a compelling new paradigm for text generation, but their training-time security remains largely unexplored. Existing backdoor attacks on Gaussian diffusion models or autoregressive…
The prompt-based learning paradigm has gained much research attention recently. It has achieved state-of-the-art performance on several NLP tasks, especially in the few-shot scenarios. While steering the downstream tasks, few works have…
Vision-Language Models (VLMs) have achieved impressive progress in multimodal text generation, yet their rapid adoption raises increasing concerns about security vulnerabilities. Existing backdoor attacks against VLMs primarily rely on…
Despite the remarkable progress of diffusion models in image generation, recent studies reveal their vulnerability to backdoor attacks via covert visual or textual triggers. Although evolving defense mechanisms can detect most existing…
Large language models (LLMs) and LLM-based agents have been widely deployed in a wide range of applications in the real world, including healthcare diagnostics, financial analysis, customer support, robotics, and autonomous driving,…