相关论文: Future Events as Backdoor Triggers: Investigating …

Backdoor attacks on reinforcement learning implant a backdoor in a victim agent's policy. Once the victim observes the trigger signal, it will switch to the abnormal mode and fail its task. Most of the attacks assume the adversary can…

Multi-modal large language models (MLLMs) extend large language models (LLMs) to process multi-modal information, enabling them to generate responses to image-text inputs. MLLMs have been incorporated into diverse multi-modal applications,…

With the widespread use of deep learning system in many applications, the adversary has strong incentive to explore vulnerabilities of deep neural networks and manipulate them. Backdoor attacks against deep neural networks have been…

Large reasoning models (LRMs) have emerged as a significant advancement in artificial intelligence, representing a specialized class of large language models (LLMs) designed to tackle complex reasoning tasks. The defining characteristic of…

This paper investigates models of event implications. Specifically, how well models predict entity state-changes, by targeting their understanding of physical attributes. Nominally, Large Language models (LLM) have been exposed to…

Deep learning models are vulnerable to backdoor attacks, where adversaries inject malicious functionality during training that activates on trigger inputs at inference time. Extensive research has focused on developing stealthy backdoor…

Precise future human motion prediction over sub-second horizons from past observations is crucial for various safety-critical applications. To date, only a few studies have examined the vulnerability of skeleton-based neural networks to…

Large vision-language models (LVLMs) have achieved impressive performance across a wide range of vision-language tasks, while they remain vulnerable to backdoor attacks. Existing backdoor attacks on LVLMs aim to force the victim model to…

Backdoor unalignment attacks against Large Language Models (LLMs) enable the stealthy compromise of safety alignment using a hidden trigger while evading normal safety auditing. These attacks pose significant threats to the applications of…

Large language models are aligned to be safe, preventing users from generating harmful content like misinformation or instructions for illegal activities. However, previous work has shown that the alignment process is vulnerable to…

Large language models (LLMs) have demonstrated impressive results on natural language tasks, and security researchers are beginning to employ them in both offensive and defensive systems. In cyber-security, there have been multiple research…

Deep speech classification has achieved tremendous success and greatly promoted the emergence of many real-world applications. However, backdoor attacks present a new security threat to it, particularly with untrustworthy third-party…

Diffusion language models (DLMs) have recently emerged as an alternative modeling paradigm to autoregressive (AR) language models, enabling parallel generation and bidirectional context modeling. Yet their security implications,…

Deep neural networks (DNNs) are vulnerable to "backdoor" poisoning attacks, in which an adversary implants a secret trigger into an otherwise normally functioning model. Detection of backdoors in trained models without access to the…

The integration of large language models (LLMs) into robotic control pipelines enables natural language interfaces that translate user prompts into executable commands. However, this digital-to-physical interface introduces a critical and…

Deep neural networks (DNNs) and natural language processing (NLP) systems have developed rapidly and have been widely used in various real-world fields. However, they have been shown to be vulnerable to backdoor attacks. Specifically, the…

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…

Large Language Models (LLMs) excel at text comprehension and generation, making them ideal for automated tasks like code review and content moderation. However, our research identifies a vulnerability: LLMs can be manipulated by…

Large language models (LLMs) are shown to benefit from chain-of-thought (COT) prompting, particularly when tackling tasks that require systematic reasoning processes. On the other hand, COT prompting also poses new vulnerabilities in the…

Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they remain vulnerable to adversarial manipulations such as jailbreaking via prompt injection attacks. These attacks bypass safety mechanisms…