Related papers: MemMark: State-Evolution Attribution Watermarking …

Large language models (LLMs) demonstrate remarkable capabilities across various tasks. However, their deployment introduces significant risks related to intellectual property. In this context, we focus on model stealing attacks, where…

Memory-augmented LLM agents offer an appealing shortcut to continual learning: rather than updating model parameters, they accumulate experience in external memory, seemingly sidestepping the stability-plasticity dilemma of parametric…

Watermarking generative-AI systems, such as LLMs, has gained considerable interest, driven by their enhanced capabilities across a wide range of tasks. Although current approaches have demonstrated that small, context-dependent shifts in…

We present the first in depth study on the robustness of existing watermarking techniques applied to code generated by large language models (LLMs). As LLMs increasingly contribute to software development, watermarking has emerged as a…

Long-term memory is essential for LLM agents that operate across multiple sessions, yet existing memory systems treat retrieval infrastructure as fixed: stored content evolves while scoring functions, fusion strategies, and…

Modern software ecosystems face a rapidly growing number of disclosed vulnerabilities, increasing the need for automated repair techniques that can operate reliably at repository scale. Although Large Language Model (LLM)-based agents have…

The huge supporting training data on the Internet has been a key factor in the success of deep learning models. However, this abundance of public-available data also raises concerns about the unauthorized exploitation of datasets for…

Watermarking techniques for large language models (LLMs), which encode hidden information in the output so its source can be verified, have gained significant attention in recent days, thanks to their potential capability to detect…

Latent diffusion models have exhibited considerable potential in generative tasks. Watermarking is considered to be an alternative to safeguard the copyright of generative models and prevent their misuse. However, in the context of model…

Existing watermarking methods for audio generative models only enable model-level attribution, allowing the identification of the originating generation model, but are unable to trace the underlying training dataset. This significant…

Assessing the veracity of online content has become increasingly critical. Large language models (LLMs) have recently enabled substantial progress in automated veracity assessment, including automated fact-checking and claim verification…

Curating high quality datasets that play a key role in the emergence of new AI applications requires considerable time, money, and computational resources. So, effective ownership protection of datasets is becoming critical. Recently, to…

Large Language Models (LLMs) have shown strong potential as conversational agents. Yet, their effectiveness remains limited by deficiencies in robust long-term memory, particularly in complex, long-term web-based services such as online…

Large language model (LLM) agents increasingly leverage long term memory to support persistent and autonomous task execution. However, this capability also introduces a new attack surface: memory poisoning, where adversaries can inject…

As artificial intelligence surpasses human capabilities in text generation, the necessity to authenticate the origins of AI-generated content has become paramount. Unbiased watermarks offer a powerful solution by embedding statistical…

The indistinguishability of large language model (LLM) output from human-authored content poses significant challenges, raising concerns about potential misuse of AI-generated text and its influence on future model training. Watermarking…

Ownership verification for neural networks is important for protecting these models from illegal copying, free-riding, re-distribution and other intellectual property misuse. We present a novel methodology for neural network ownership…

With the growing demand for intelligent in-vehicle experiences, vehicle-based agents are evolving from simple assistants to long-term companions. This evolution requires agents to continuously model multi-user preferences and make reliable…

Large language models face challenges in long-context question answering, where key evidence of a query may be dispersed across millions of tokens. Existing works equip large language models with a memory buffer that is dynamically updated…

Watermarking has emerged as a promising technique to track AI-generated content and differentiate it from authentic human creations. While prior work extensively studies watermarking for autoregressive large language models (LLMs) and image…