相关论文: WAInjectBench: Benchmarking Prompt Injection Detec…

With the integration of large language models (LLMs), embodied agents have strong capabilities to understand and plan complicated natural language instructions. However, a foreseeable issue is that those embodied agents can also flawlessly…

Adversarial attacks present a significant threat to modern machine learning systems. Yet, existing detection methods often lack the ability to detect unseen attacks or detect different attack types with a high level of accuracy. In this…

Deep neural networks (DNNs) offer significant promise for improving breast cancer diagnosis in medical imaging. However, these models are highly susceptible to adversarial attacks--small, imperceptible changes that can mislead…

Recent studies have shown that state-of-the-art deep learning models are vulnerable to the inputs with small perturbations (adversarial examples). We observe two critical obstacles in adversarial examples: (i) Strong adversarial attacks…

AI agents such as OpenClaw are increasingly deployed in local workflows with access to external tools. This creates indirect prompt-injection (IPI) risk: an agent may execute harmful instructions embedded in untrusted inputs such as email,…

Navigation agents powered by large language models (LLMs) convert natural language instructions into executable plans and actions. Compared to text-based applications, their security is far more critical: a successful prompt injection…

Large Language Models (LLMs) are widely deployed in applications that accept user-submitted content, such as uploaded documents or pasted text, for tasks like summarization and question answering. In this paper, we identify a new class of…

Object detectors are vulnerable to backdoor attacks. In contrast to classifiers, detectors possess unique characteristics, architecturally and in task execution; often operating in challenging conditions, for instance, detecting traffic…

Adversarial examples are well-known tools to evaluate the vulnerability of deep neural networks (DNNs). Although lots of adversarial attack algorithms have been developed, it's still challenging in the practical scenario that the model's…

Recent advances in browser-based LLM agents have shown promise for automating tasks ranging from simple form filling to hotel booking or online shopping. Current benchmarks measure agent performance in controlled environments, such as…

Deep Neural Networks (DNNs) are notoriously vulnerable to adversarial input designs with limited noise budgets. While numerous successful attacks with subtle modifications to original input have been proposed, defense techniques against…

Autonomous agents deployed in the real world need to be robust against adversarial attacks on sensory inputs. Robustifying agent policies requires anticipating the strongest attacks possible. We demonstrate that existing observation-space…

Most of the intrusion detection methods in computer networks are based on traffic flow characteristics. However, this approach may not fully exploit the potential of deep learning algorithms to directly extract features and patterns from…

With the rapid development of Large Language Models (LLMs), numerous mature applications of LLMs have emerged in the field of content safety detection. However, we have found that LLMs exhibit blind trust in safety detection agents. The…

Fault injections are increasingly used to attack/test secure applications. In this paper, we define formal models of runtime monitors that can detect fault injections that result in test inversion attacks and arbitrary jumps in the control…

We describe WebSuite, the first diagnostic benchmark for generalist web agents, designed to systematically evaluate why agents fail. Advances in AI have led to the rise of numerous web agents that autonomously operate a browser to complete…

Language models remain vulnerable to prompt injection attacks despite extensive safety training. We trace this failure to role confusion: models infer the source of text based on how it sounds, not where it actually comes from. A command…

The existence of adversarial attacks on convolutional neural networks (CNN) questions the fitness of such models for serious applications. The attacks manipulate an input image such that misclassification is evoked while still looking…

Research of adversarial attacks is important for AI security because it shows the vulnerability of deep learning models and helps to build more robust models. Adversarial attacks on images are most widely studied, which include noise-based…

Website fingerprinting (WF) attacks identify the websites visited over anonymized connections by analyzing patterns in network traffic flows, such as packet sizes, directions, or interval times using a machine learning classifier. Previous…