Related papers: Reverse CAPTCHA: Evaluating LLM Susceptibility to …

As LLM-based computer-use agents (CUAs) begin to autonomously interact with real-world interfaces, understanding their vulnerability to manipulative interface designs becomes increasingly critical. We introduce SusBench, an online benchmark…

This research addresses a fundamental question in AI: whether large language models truly understand concepts or simply recognize patterns. The authors propose bidirectional reasoning,the ability to apply transformations in both directions…

System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive…

With their increasing size, large language models (LLMs) are becoming increasingly good at language understanding tasks. But even with high performance on specific downstream task, LLMs fail at simple linguistic tests for negation or…

Unlearning seeks to remove specific knowledge from large language models (LLMs), but its effectiveness remains contested. On one side, "forgotten" knowledge can often be recovered through interventions such as light fine-tuning; on the…

Large language models (LLMs) can understand human instructions, showing their potential for pragmatic applications beyond traditional NLP tasks. However, they still struggle with complex instructions, which can be either complex task…

Large language models for code (Code LLM) are increasingly utilized in programming environments. Despite their utility, the training datasets for top LLM remain undisclosed, raising concerns about potential copyright violations. Some…

Text CAPTCHA has been an effective means to protect online systems from spams and abuses caused by automatic scripts which pretend to be human beings. However, nearly all the Text CAPTCHA designs in nowadays are based on English characters,…

This study reveals a previously unexplored vulnerability in the safety alignment of Large Language Models (LLMs). Existing aligned LLMs predominantly respond to unsafe queries with refusals, which often begin with a fixed set of prefixes…

Although multimodal large language models (MLLMs) are increasingly deployed in real-world applications, their instruction-following behavior leaves them vulnerable to prompt injection attacks. Existing prompt injection methods predominantly…

Recent releases of Large Language Models (LLMs), e.g. ChatGPT, are astonishing at generating human-like texts, but they may impact the authenticity of texts. Previous works proposed methods to detect these AI-generated texts, including…

The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that…

Language Models (LMs) are prone to ''memorizing'' training data, including substantial sensitive user information. To mitigate privacy risks and safeguard the right to be forgotten, machine unlearning has emerged as a promising approach for…

Large Language Models (LLMs) are increasingly integrated into software engineering workflows, yet current benchmarks provide only coarse performance summaries that obscure the diverse capabilities and limitations of these models. This paper…

UI automation is a useful technique for UI testing, bug reproduction, and robotic process automation. Recording user actions with an application assists rapid development of UI automation scripts, but existing recording techniques are…

Work on scaling laws has found that large language models (LMs) show predictable improvements to overall loss with increased scale (model size, training data, and compute). Here, we present evidence for the claim that LMs may show inverse…

Machine learning models that first learn a representation of a domain in terms of human-understandable concepts, then use it to make predictions, have been proposed to facilitate interpretation and interaction with models trained on…

Language models can be viewed as functions that embed text into Euclidean space, where the quality of the embedding vectors directly determines model performance, training such neural networks involves various uncertainties. This paper…

Standard evaluation protocols reveal a counterintuitive phenomenon: on 7.7% of benchmark problems spanning five datasets, larger language models underperform smaller ones by 28.4 percentage points despite 10-100x more parameters. Through…

Deep learning has recently demonstrated state-of-the art performance on key tasks related to the maintenance of computer systems, such as intrusion detection, denial of service attack detection, hardware and software system failures, and…