相关论文: Preference Redirection via Attention Concentration…

Adversarial attacks have evolved from simply disrupting predictions on conventional task-specific models to the more complex goal of manipulating image semantics on Large Vision-Language Models (LVLMs). However, existing methods struggle…

Backdoor attacks pose a serious threat to deep learning models by allowing adversaries to implant hidden behaviors that remain dormant on clean inputs but are maliciously triggered at inference. Existing backdoor attack methods typically…

Recent advances in natural language processing and the increased use of large language models have exposed new security vulnerabilities, such as backdoor attacks. Previous backdoor attacks require input manipulation after model distribution…

With the widespread deployment of Computer-using Agents (CUAs) in complex real-world environments, prevalent long-term risks often lead to severe and irreversible consequences. Most existing guardrails for CUAs adopt a reactive approach,…

The rise of pre-trained unified foundation models breaks down the barriers between different modalities and tasks, providing comprehensive support to users with unified architectures. However, the backdoor attack on pre-trained models poses…

Machine learning (ML) models have significantly grown in complexity and utility, driving advances across multiple domains. However, substantial computational resources and specialized expertise have historically restricted their wide…

Large language models (LLMs)-powered AI agents exhibit a high level of autonomy in addressing medical and healthcare challenges. With the ability to access various tools, they can operate within an open-ended action space. However, with the…

Increasing use of machine learning (ML) technologies in privacy-sensitive domains such as medical diagnoses, lifestyle predictions, and business decisions highlights the need to better understand if these ML technologies are introducing…

The emergence of LLM (Large Language Model) integrated virtual assistants has brought about a rapid transformation in communication dynamics. During virtual assistant development, some developers prefer to leverage the system message, also…

Adversarial attacks constitute a notable threat to machine learning systems, given their potential to induce erroneous predictions and classifications. However, within real-world contexts, the essential specifics of the deployed model are…

The emergence of Large Language Models (LLMs) has significantly advanced solutions across various domains, from political science to software development. However, these models are constrained by their training data, which is static and…

A high volume of recent ML security literature focuses on attacks against aligned large language models (LLMs). These attacks may extract private information or coerce the model into producing harmful outputs. In real-world deployments,…

Large Language Models (LLMs) have become integral to automated code analysis, enabling tasks such as vulnerability detection and code comprehension. However, their integration introduces novel attack surfaces. In this paper, we identify and…

In shilling attacks, an adversarial party injects a few fake user profiles into a Recommender System (RS) so that the target item can be promoted or demoted. Although much effort has been devoted to developing shilling attack methods, we…

We present a novel attention mechanism: Causal Attention (CATT), to remove the ever-elusive confounding effect in existing attention-based vision-language models. This effect causes harmful bias that misleads the attention module to focus…

With the advancement of vision transformers (ViTs) and self-supervised learning (SSL) techniques, pre-trained large ViTs have become the new foundation models for computer vision applications. However, studies have shown that, like…

Advertising channels have evolved from conventional print media, billboards and radio advertising to online digital advertising (ad), where the users are exposed to a sequence of ad campaigns via social networks, display ads, search etc.…

Despite the substantial advancements in Vision-Language Pre-training (VLP) models, their susceptibility to adversarial attacks poses a significant challenge. Existing work rarely studies the transferability of attacks on VLP models,…

Projector-based adversarial attack aims to project carefully designed light patterns (i.e., adversarial projections) onto scenes to deceive deep image classifiers. It has potential applications in privacy protection and the development of…

Pre-trained language models (PLMs) are shown to be vulnerable to minor word changes, which poses a big threat to real-world systems. While previous studies directly focus on manipulating word inputs, they are limited by their means of…