相关论文: Assimilation Matters: Model-level Backdoor Detecti…

Deep learning models have achieved unprecedented performance in the domain of object detection, resulting in breakthroughs in areas such as autonomous driving and security. However, deep learning models are vulnerable to backdoor attacks.…

Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce…

In recent years, foundation models (FMs) have solidified their role as cornerstone advancements in the deep learning domain. By extracting intricate patterns from vast datasets, these models consistently achieve state-of-the-art results…

Cyber attacks are often identified using system and network logs. There have been significant prior works that utilize provenance graphs and ML techniques to detect attacks, specifically advanced persistent threats, which are very difficult…

Vision-Language Models (VLMs), such as CLIP, have demonstrated remarkable zero-shot generalizability across diverse downstream tasks. However, recent studies have revealed that VLMs, including CLIP, are highly vulnerable to adversarial…

Fine-tuning vision-language models (VLMs) such as CLIP often leads to catastrophic forgetting of pretrained knowledge. Prior work primarily aims to mitigate forgetting during adaptation; however, forgetting often remains inevitable during…

Visual Language Models (VLMs) are vulnerable to adversarial attacks, especially those from adversarial images, which is however under-explored in literature. To facilitate research on this critical safety problem, we first construct a new…

Most existing methods to detect backdoored machine learning (ML) models take one of the two approaches: trigger inversion (aka. reverse engineer) and weight analysis (aka. model diagnosis). In particular, the gradient-based trigger…

Large Vision-Language Models (LVLMs) can be vulnerable to adversarial images that subtly bias their outputs toward plausible yet incorrect responses. We introduce a general, efficient, and training-free defense that combines image…

The widespread use of cameras in our society has created an overwhelming amount of video data, far exceeding the capacity for human monitoring. This presents a critical challenge for public safety and security, as the timely detection of…

Advanced persistent threats (APTs) are sophisticated cyber attacks that can remain undetected for extended periods, making their mitigation particularly challenging. Given their persistence, significant effort is required to detect them and…

Vision-language models (VLMs), such as CLIP, have gained popularity for their strong open vocabulary classification performance, but they are prone to assigning high confidence scores to misclassifications, limiting their reliability in…

Backdoor attacks have been shown to impose severe threats to real security-critical scenarios. Although previous works can achieve high attack success rates, they either require access to victim models which may significantly reduce their…

Fine-tuning is an essential process to improve the performance of Large Language Models (LLMs) in specific domains, with Parameter-Efficient Fine-Tuning (PEFT) gaining popularity due to its capacity to reduce computational demands through…

Anomaly detection (AD) is an important machine learning task with applications in fraud detection, content moderation, and user behavior analysis. However, AD is relatively understudied in a natural language processing (NLP) context,…

Designing robust machine learning systems remains an open problem, and there is a need for benchmark problems that cover both environmental changes and evaluation on a downstream task. In this work, we introduce AVOIDDS, a realistic object…

Vision-language models (VLMs) are increasingly deployed as trusted authorities -- fact-checking images on social media, comparing products, and moderating content. Users implicitly trust that these systems perceive the same visual content…

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…

Person re-identification (re-id) models are vital in security surveillance systems, requiring transferable adversarial attacks to explore the vulnerabilities of them. Recently, vision-language models (VLM) based attacks have shown superior…

Downstream fine-tuning of vision-language-action (VLA) models enhances robotics, yet exposes the pipeline to backdoor risks. Attackers can pretrain VLAs on poisoned data to implant backdoors that remain stealthy but can trigger harmful…