相关论文: Exposing Hidden Interfaces: LLM-Guided Type Infere…

Large language model (LLM) agents have demonstrated remarkable capabilities in complex reasoning and decision-making by leveraging external tools. However, this tool-centric paradigm introduces a previously underexplored attack surface,…

User profiling, as a core technique for user understanding, aims to infer structural attributes from user information. Large Language Models (LLMs) provide a promising avenue for user profiling, yet the progress is hindered by the lack of…

LLM-based equation discovery offers a promising route to recovering symbolic laws from data, but many systems still rely on generation-centered loops that propose candidates, fit parameters, score results, and reuse selected examples. Such…

Backdoor attacks are among the most effective, practical, and stealthy attacks in deep learning. In this paper, we consider a practical scenario where a developer obtains a deep model from a third party and uses it as part of a…

Biases and errors in human-labeled data present significant challenges for machine learning, especially in supervised learning reliant on potentially flawed ground truth data. These flaws, including diagnostic errors and societal biases,…

Privacy-preserving inference in edge computing paradigms encourages the users of machine-learning services to locally run a model on their private input and only share the models outputs for a target task with the server. We study how a…

With the recent surge of language models in different applications, attention to safety and robustness of these models has gained significant importance. Here we introduce a joint framework in which we simultaneously probe and improve the…

Text-to-Image (T2I) models generate high-quality images but are vulnerable to malicious backdoor attacks that inject harmful biases (e.g., trigger-activated gender or racial stereotypes). Existing debiasing methods, often designed for…

Autonomous program improvement typically involves automatically producing bug fixes and feature additions. Such program improvement can be accomplished by a combination of large language model (LLM) and program analysis capabilities, in the…

In recent years, deep neural networks have been widely used for building high-performance Artificial Intelligence (AI) systems for computer vision applications. Object detection is a fundamental task in computer vision, which has been…

Version control relies on commit messages to convey the rationale for code changes, but these messages are often low quality and, more critically, inconsistent with their diffs-known as message-code inconsistency (MCI). MCIs mislead…

Natural language processing (NLP) has seen remarkable advancements with the development of large language models (LLMs). Despite these advancements, LLMs often produce socially biased outputs. Recent studies have mainly addressed this…

Protecting the confidentiality of private data and using it for useful collaboration have long been at odds. Modern cryptography is bridging this gap through rapid growth in secure protocols such as multi-party computation,…

We present MAFA (Multi-Agent Framework for Annotation), a production-deployed system that transforms enterprise-scale annotation workflows through configurable multi-agent collaboration. Addressing the critical challenge of annotation…

Large language models can consult information that fixed static analyzers cannot, such as documentation, current security advisories, version-specific metadata, and informal API contracts. This makes LLMs a compelling option for program…

Large language models (LLMs) have proven to be very capable, but access to frontier models currently relies on inference providers. This introduces trust challenges: how can we be sure that the provider is using the model configuration they…

Autonomous multi-agent systems (MAS) are useful for automating complex tasks but raise trust concerns due to risks such as miscoordination or goal misalignment. Explainability is vital for users' trust calibration, but explainable MAS face…

We introduce MIM (Masked Image Modeling)-Refiner, a contrastive learning boost for pre-trained MIM models. MIM-Refiner is motivated by the insight that strong representations within MIM models generally reside in intermediate layers.…

The dominance of proprietary LLMs has led to restricted access and raised information privacy concerns. High-performing open-source alternatives are crucial for information-sensitive and high-volume applications but often lag behind in…

Large language models (LLMs) are increasingly integrated into autonomous systems, giving rise to a new class of software known as Agentware, where LLM-powered agents perform complex, open-ended tasks in domains such as software engineering,…