English
Related papers

Related papers: OptiLeak: Efficient Prompt Reconstruction via Rein…

200 papers

When using an LLM to process text outside the training domain(s), an often overlooked factor is vocabulary mismatch, where the general-domain tokenizer fails to capture frequent domain-specific terms, leading to higher token fertility and…

Computation and Language · Computer Science 2025-10-01 Christian Herold , Michael Kozielski , Nicholas Santavas , Yannick Versley , Shahram Khadivi

AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incorporating external content into the generation pipeline can weaken the safety alignment mechanisms…

Computation and Language · Computer Science 2026-05-29 Aditya Nawal , Manit Baser , Mohan Gurusamy

Large language models (LLMs) have shown great promise in recommender systems, where supervised fine-tuning (SFT) is commonly used for adaptation. Subsequent studies further introduce preference learning to incorporate negative samples into…

Information Retrieval · Computer Science 2026-02-20 Bingqian Li , Bowen Zheng , Xiaolei Wang , Long Zhang , Jinpeng Wang , Sheng Chen , Wayne Xin Zhao , Ji-rong Wen

Reinforcement Learning from Human Feedback (RLHF) has become the standard for aligning Large Language Models (LLMs), yet its efficacy is bottlenecked by the high cost of acquiring preference data, especially in low-resource and expert…

Machine Learning · Computer Science 2026-03-11 Davit Melikidze , Marian Schneider , Jessica Lam , Martin Wertich , Ido Hakimi , Barna Pásztor , Andreas Krause

Efficient red-teaming method to uncover vulnerabilities in Large Language Models (LLMs) is crucial. While recent attacks often use LLMs as optimizers, the discrete language space make gradient-based methods struggle. We introduce LARGO…

Machine Learning · Computer Science 2025-05-19 Ran Li , Hao Wang , Chengzhi Mao

Network slicing in 5G and the future 6G networks will enable the creation of multiple virtualized networks on a shared physical infrastructure. This innovative approach enables the provision of tailored networks to accommodate specific…

Cryptography and Security · Computer Science 2024-09-18 Wei Shao , Chandra Thapa , Rayne Holland , Sarah Ali Siddiqui , Seyit Camtepe

High-privilege LLM agents that autonomously process external documentation are increasingly trusted to automate tasks by reading and executing project instructions, yet they are granted terminal access, filesystem control, and outbound…

Cryptography and Security · Computer Science 2026-03-13 Ching-Yu Kao , Xinfeng Li , Shenyu Dai , Tianze Qiu , Pengcheng Zhou , Eric Hanchen Jiang , Philip Sperl

The increasing complexity of large language models (LLMs) raises concerns about their ability to "cheat" on standard Question Answering (QA) benchmarks by memorizing task-specific data. This undermines the validity of benchmark evaluations,…

Computation and Language · Computer Science 2025-09-16 Yixiong Fang , Tianran Sun , Yuling Shi , Min Wang , Xiaodong Gu

LLM-assisted defect discovery has a precision crisis: plausible-but-wrong reports overwhelm maintainers and degrade credibility for real findings. We present Refute-or-Promote, an inference-time reliability pattern combining Stratified…

Cryptography and Security · Computer Science 2026-04-22 Abhinav Agarwal

In the digital era, accidental exposure of sensitive information such as API keys, tokens, and credentials is a growing security threat. While most prior work focuses on detecting secrets in source code, leakage in software issue reports…

Software Engineering · Computer Science 2026-04-17 Sadif Ahmed , Md Nafiu Rahman , Zahin Wahab , Gias Uddin , Rifat Shahriyar

Large language models (LLMs) are known to be vulnerable to jailbreak attacks, which typically rely on carefully designed prompts containing explicit semantic structure. These attacks generally operate by fixing an adversarial instruction…

Machine Learning · Computer Science 2026-05-07 Marco Rando , Samuel Vaiter

Trustworthy language models should provide both correct and verifiable answers. However, citations generated directly by standalone LLMs are often unreliable. As a result, current systems insert citations by querying an external retriever…

Artificial Intelligence · Computer Science 2026-04-07 Yukun Huang , Sanxing Chen , Jian Pei , Manzil Zaheer , Bhuwan Dhingra

LLM agents are increasingly relevant to research domains such as vulnerability discovery. Yet, the strongest systems remain closed and cloud-only, making them resource-intensive, difficult to reproduce, and unsuitable for work involving…

Cryptography and Security · Computer Science 2026-03-19 Philipp Normann , Andreas Happe , Jürgen Cito , Daniel Arp

Online Kernel Learning (OKL) has attracted considerable research interest due to its promising predictive performance in streaming environments. Second-order approaches are particularly appealing for OKL as they often offer substantial…

Machine Learning · Computer Science 2025-06-17 Dongxie Wen , Xiao Zhang , Zhewei Wei , Chenping Hou , Shuai Li , Weinan Zhang

Large language models (LLMs) have demonstrated impressive performance and have come to dominate the field of natural language processing (NLP) across various tasks. However, due to their strong instruction-following capabilities and…

Cryptography and Security · Computer Science 2026-04-10 Yulin Chen , Haoran Li , Yuan Sui , Yue Liu , Yufei He , Xiaoling Bai , Chi Fei , Yabo Li , Haozhe Ma , Yangqiu Song , Bryan Hooi

Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features using the complementary strengths of various data modalities. However, the open nature of such systems inadvertently increases the…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Siyuan Liang , Kuanrong Liu , Jiajun Gong , Jiawei Liang , Yuan Xun , Ee-Chien Chang , Xiaochun Cao

This paper demonstrates a new side-channel that enables an adversary to extract sensitive information about inference inputs in large language models (LLMs) based on the number of output tokens in the LLM response. We construct attacks…

Machine Learning · Computer Science 2024-12-23 Tianchen Zhang , Gururaj Saileshwar , David Lie

Federated Learning (FL) enables collaborative training of Large Language Models (LLMs) across distributed data sources while preserving privacy. However, when federated LLMs are deployed in critical applications, it remains unclear which…

Machine Learning · Computer Science 2026-01-29 Waris Gill , Ahmad Humayun , Ali Anwar , Muhammad Ali Gulzar

System prompts are widely used to guide the outputs of large language models (LLMs). These prompts often contain business logic and sensitive information, making their protection essential. However, adversarial and even regular user queries…

Cryptography and Security · Computer Science 2025-08-28 Zhifeng Jiang , Zhihua Jin , Guoliang He

Recent advances have demonstrated that large language models (LLMs) excel as listwise rerankers, but their high computational demands remain a barrier to widespread adoption. Further, the traditional language modeling (LM) objective is not…

Information Retrieval · Computer Science 2024-11-13 Zijian Chen , Ronak Pradeep , Jimmy Lin