相关论文: WAInjectBench: Benchmarking Prompt Injection Detec…

Recent advances in large text-conditional diffusion models have revolutionized image generation by enabling users to create realistic, high-quality images from textual prompts, significantly enhancing artistic creation and visual…

Recent advances in Vision-Language Models (VLMs) facilitate a new class of embodied AI systems, where these models are integrated into physical platforms, e.g. robots and autonomous vehicles, to interpret visual scenes and execute natural…

We study backdoor poisoning attacks against image classification networks, whereby an attacker inserts a trigger into a subset of the training data, in such a way that at test time, this trigger causes the classifier to predict some target…

Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word…

Web agents, powered by large language models (LLMs), are increasingly deployed to automate complex web interactions. The rise of open-source frameworks (e.g., Browser Use, Skyvern-AI) has accelerated adoption, but also broadened the attack…

LLM as judge systems used to assess text quality code correctness and argument strength are vulnerable to prompt injection attacks. We introduce a framework that separates content author attacks from system prompt attacks and evaluate five…

Nowadays, powerful large language models (LLMs) such as ChatGPT have demonstrated revolutionary power in a variety of tasks. Consequently, the detection of machine-generated texts (MGTs) is becoming increasingly crucial as LLMs become more…

Watermarking combines an imperceptible change to an input image that will trigger a detector, to assert provenance and protect intellectual property. The literature has shown great interest in attacks on watermarking schemes: attackers are…

In this paper, we investigate data-driven attack detection and identification in a model-free setting. We consider a practically motivated scenario in which the available dataset may be compromised by malicious sensor attacks, but contains…

Adversarial attacks pose significant challenges for detecting adversarial attacks at an early stage. We propose attack-agnostic detection on reinforcement learning-based interactive recommendation systems. We first craft adversarial…

Website Fingerprinting (WF) attacks exploit patterns in encrypted traffic to infer the websites visited by users, posing a serious threat to anonymous communication systems. Although recent WF techniques achieve over 90% accuracy in…

Large Language Models (LLMs) are increasingly deployed in agentic systems that interact with an untrusted environment. However, LLM agents are vulnerable to prompt injection attacks when handling untrusted data. In this paper we propose…

Most LLM safety work studies single-agent models, but many real applications rely on multiple interacting agents. In these systems, prompt segmentation and inter-agent routing create attack surfaces that single-agent evaluations miss. We…

Tool selection is a key component of LLM agents. A popular approach follows a two-step process - \emph{retrieval} and \emph{selection} - to pick the most appropriate tool from a tool library for a given task. In this work, we introduce…

Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical security vulnerabilities. However, the existing literature…

Model Inversion (MI) attacks aim at leveraging the output information of target models to reconstruct privacy-sensitive training data, raising critical concerns regarding the privacy vulnerabilities of Deep Neural Networks (DNNs).…

LLM-based web agents have become increasingly popular for their utility in daily life and work. However, they exhibit critical vulnerabilities when processing malicious URLs: accepting a disguised malicious URL enables subsequent access to…

Agent hijacking, highlighted by OWASP as a critical threat to the Large Language Model (LLM) ecosystem, enables adversaries to manipulate execution by injecting malicious instructions into retrieved content. Most existing attacks rely on…

Prompt injection attacks pose serious security risks across a wide range of real-world applications. While receiving increasing attention, the community faces a critical gap: the lack of a unified platform for prompt injection evaluation.…

Adversarial attacks pose a significant threat to machine learning models by inducing incorrect predictions through imperceptible perturbations to input data. While these attacks are well studied in unstructured domains such as images, their…