Related papers: SCOPE: Intrinsic Semantic Space Control for Mitiga…

Recent studies have shown that large language models (LLMs) can infer private user attributes (e.g., age, location, gender) from user-generated text shared online, enabling rapid and large-scale privacy breaches. Existing…

Large Language Models (LLMs) have transformed natural language processing, yet their internal mechanisms remain largely opaque. Recently, mechanistic interpretability has attracted significant attention from the research community as a…

Assessing whether AI-generated images are substantially similar to source works is a crucial step in resolving copyright disputes. In this paper, we propose CopyJudge, a novel automated infringement identification framework that leverages…

In this paper, we propose SCANING, an unsupervised framework for paraphrasing via controlled noise injection. We focus on the novel task of paraphrasing algebraic word problems having practical applications in online pedagogy as a means to…

Large Language Models (LLMs) are increasingly fine-tuned on smaller, domain-specific datasets to improve downstream performance. These datasets often contain proprietary or copyrighted material, raising the need for reliable safeguards…

Sparse autoencoders (SAEs) are useful for detecting and steering interpretable features in neural networks, with particular potential for understanding complex multimodal representations. Given their ability to uncover interpretable…

Large language models have achieved remarkable capabilities across diverse tasks, yet their internal decision-making processes remain largely opaque, limiting our ability to inspect, control, and systematically improve them. This opacity…

Recent advances in image-level self-supervised learning (SSL) have made significant progress, yet learning dense representations for patches remains challenging. Mainstream methods encounter an over-dispersion phenomenon that patches from…

There is growing interest in leveraging mechanistic interpretability and controllability to better understand and influence the internal dynamics of large language models (LLMs). However, current methods face fundamental challenges in…

With the wide adoption of personal AI assistants such as OpenClaw, privacy leakage in user interaction contexts with large language model (LLM) agents has become a critical issue. Existing privacy attacks against LLMs primarily target…

Various strategies for label-scarce object detection have been explored by the computer vision research community. These strategies mainly rely on assumptions that are specific to natural images and not directly applicable to the biological…

Pre-trained Large Language Models (LLMs) have demonstrated remarkable capabilities but also pose risks by learning and generating copyrighted material, leading to significant legal and ethical concerns. In a potential real-world scenario,…

We study how reliably sparse autoencoders (SAEs) support claims about reasoning-related internal features in large language models. We first give a stylized analysis showing that sparsity-regularized decoding can preferentially retain…

Real-world autonomous driving must adhere to complex human social rules that extend beyond legally codified traffic regulations. Many of these semantic constraints, such as yielding to emergency vehicles, complying with traffic officers'…

Image embeddings are generally assumed to pose limited privacy risk. We challenge this assumption by formalizing semantic leakage as the ability to recover semantic structures from compressed image embeddings. Surprisingly, we show that…

Dense embeddings deliver strong retrieval performance but often lack interpretability and controllability. This paper introduces a novel approach using sparse autoencoders (SAE) to interpret and control dense embeddings via the learned…

Watermarking the initial noise of diffusion models has emerged as a promising approach for image provenance, but content-independent noise patterns can be forged via inversion and regeneration attacks. Recent semantic-aware watermarking…

Sparse Autoencoders (SAEs) have recently gained attention as a means to improve the interpretability and steerability of Large Language Models (LLMs), both of which are essential for AI safety. In this work, we extend the application of…

The general-purpose nature of Large Language Models (LLMs) presents a significant challenge for domain-specific applications, often leading to out-of-domain (OOD) interactions that undermine the provider's intent. Existing methods for…

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing but also pose significant privacy risks by memorizing and leaking Personally Identifiable Information (PII). Existing mitigation…