相关论文: SusBench: An Online Benchmark for Evaluating Dark …

CAPTCHAs have been a critical bottleneck for deploying web agents in real-world applications, often blocking them from completing end-to-end automation tasks. While modern multimodal LLM agents have demonstrated impressive performance in…

Advances in natural language processing and understanding have led to a rapid growth in the popularity of conversational user interfaces (CUIs). While CUIs introduce novel benefits, they also yield risks that may exploit people's trust.…

We introduce ISO-Bench, a benchmark for coding agents to test their capabilities on real-world inference optimization tasks. These tasks were taken from vLLM and SGLang, two of the most popular LLM serving frameworks. Each task provides an…

Manipulation defines many of our experiences as a consumer, including subtle nudges and overt advertising campaigns that seek to gain our attention and money. With the advent of digital services that can continuously optimize online…

The advancement of AI technologies, particularly Large Language Models (LLMs), has transformed computing while introducing new security and privacy risks. Prior research shows that cybercriminals are increasingly leveraging uncensored LLMs…

The problem of ``Dark Patterns" in user interface/user experience (UI/UX) design has proven a difficult issue to tackle. Malicious and explotitative design has expanded to multiple domains in the past 10 years and which has in turn led to…

LLM-based agents are becoming increasingly proficient at solving web-based tasks. With this capability comes a greater risk of misuse for malicious purposes, such as posting misinformation in an online forum or selling illicit substances on…

Autonomous computer use agents that powered by multimodal large language models (MLLMs) are emerging as capable assistants for completing complex digital workflows. However, real-world execution environments are far from ideal: pop-ups,…

Context: Dark patterns are user interface or other software designs that deceive or manipulate users to do things they would not otherwise do. Even though dark patterns have been under active research for a long time, including particularly…

Large language models (LLMs) have evolved into interactive agents that collaborate with users in real-world tasks. Effective collaboration in such settings increasingly depends on understanding the user beyond what is explicitly stated, as…

While LLM-Based agents, which use external tools to solve complex problems, have made significant progress, benchmarking their ability is challenging, thereby hindering a clear understanding of their limitations. In this paper, we propose…

The potential of Large Language Model (LLM) as agents has been widely acknowledged recently. Thus, there is an urgent need to quantitatively \textit{evaluate LLMs as agents} on challenging tasks in interactive environments. We present…

Autonomous unmanned aerial vehicle (UAV) systems are increasingly deployed in safety-critical, networked environments where they must operate reliably in the presence of malicious adversaries. While recent benchmarks have evaluated large…

Dark patterns are deceptive user interfaces employed by e-commerce websites to manipulate user's behavior in a way that benefits the website, often unethically. This study investigates the detection of such dark patterns. Existing solutions…

Deepfakes are computationally-created entities that falsely represent reality. They can take image, video, and audio modalities, and pose a threat to many areas of systems and societies, comprising a topic of interest to various aspects of…

Language models (LMs) have achieved impressive accuracy across a variety of tasks but remain vulnerable to high-confidence misclassifications, also referred to as unknown unknowns (UUs). These UUs cluster into blind spots in the feature…

Current Large Language Models (LLMs) are gradually exploited in practically valuable agentic workflows such as Deep Research, E-commerce recommendation, and job recruitment. In these applications, LLMs need to select some optimal solutions…

Although deceptive design patterns are subject to growing regulatory oversight, enforcement races to keep up with the scale of the problem. One promising solution is automated detection tools, many of which are developed within academia. We…

As language models (LMs) are used to build autonomous agents in real environments, ensuring their adversarial robustness becomes a critical challenge. Unlike chatbots, agents are compound systems with multiple components taking actions,…

As LLMs are increasingly integrated into systems that browse, retrieve, summarize, and act on web content, webpages have become an untrusted input vector for downstream model behavior. This enables site owners, contributors, and adversaries…