English
Related papers

Related papers: LLM Watermark Evasion via Bias Inversion

200 papers

Large Language Models (LLMs) are known to be vulnerable to jailbreak attacks. An important observation is that, while different types of jailbreak attacks can generate significantly different queries, they mostly result in similar responses…

Cryptography and Security · Computer Science 2025-05-21 Zhexin Zhang , Junxiao Yang , Yida Lu , Pei Ke , Shiyao Cui , Chujie Zheng , Hongning Wang , Minlie Huang

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…

Cryptography and Security · Computer Science 2023-06-27 Feisi Fu , Wenchao Li

The known stylistic biases in LLM judges, such as a preference for verbosity or specific sentence structures, present an underexplored security vulnerability. In this work, we introduce BITE (BIas exploraTion and Exploitation), a black-box…

Cryptography and Security · Computer Science 2026-05-29 Xianglin Yang , Bryan Hooi , Gelei Deng , Tianwei Zhang , Jin Song Dong

There is growing interest in ensuring that large language models (LLMs) align with human values. However, the alignment of such models is vulnerable to adversarial jailbreaks, which coax LLMs into overriding their safety guardrails. The…

Machine Learning · Computer Science 2024-07-22 Patrick Chao , Alexander Robey , Edgar Dobriban , Hamed Hassani , George J. Pappas , Eric Wong

Large Language Models (LLMs) guardrail systems are designed to protect against prompt injection and jailbreak attacks. However, they remain vulnerable to evasion techniques. We demonstrate two approaches for bypassing LLM prompt injection…

Cryptography and Security · Computer Science 2025-07-15 William Hackett , Lewis Birch , Stefan Trawicki , Neeraj Suri , Peter Garraghan

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…

Computer Science and Game Theory · Computer Science 2026-05-15 Juho Kim , Fei Fang , Tuomas Sandholm

Although large language models (LLMs) demonstrate impressive proficiency in various tasks, they present potential safety risks, such as `jailbreaks', where malicious inputs can coerce LLMs into generating harmful content bypassing safety…

Computation and Language · Computer Science 2025-11-26 Isack Lee , Haebin Seong

While effective backdoor detection and inversion schemes have been developed for AIs used e.g. for images, there are challenges in "porting" these methods to LLMs. First, the LLM input space is discrete, which precludes gradient-based…

Machine Learning · Computer Science 2025-09-22 Zhengxing Li , Guangmingmei Yang , Jayaram Raghuram , David J. Miller , George Kesidis

LLM watermarks allow tracing AI-generated texts by inserting a detectable signal into their generated content. Recent works have proposed a wide range of watermarking algorithms, each with distinct designs, usually built using a bottom-up…

Cryptography and Security · Computer Science 2026-02-09 Thibaud Gloaguen , Robin Staab , Nikola Jovanović , Martin Vechev

Sandbox evasion remains a critical challenge for automated malware analysis, as modern malware employs environment checks to detect analysis platforms and suppress malicious behavior. Existing approaches rely on manually crafted bypass…

Cryptography and Security · Computer Science 2026-05-22 Zhiyong Sui , Lamine Noureddine , Mst Eshita Khatun , Sideeq Bello , Justin Woodring , Aisha Ali-Gombe

Diffusion large language models (dLLMs) offer faster generation than autoregressive models while maintaining comparable quality, but existing watermarking methods fail on them due to their non-sequential decoding. Unlike autoregressive…

Machine Learning · Computer Science 2025-10-06 Linyu Wu , Linhao Zhong , Wenjie Qu , Yuexin Li , Yue Liu , Shengfang Zhai , Chunhua Shen , Jiaheng Zhang

Large language models (LLMs) are inherently vulnerable to unintended privacy breaches. Consequently, systematic red-teaming research is essential for developing robust defense mechanisms. However, current data extraction methods suffer from…

Machine Learning · Computer Science 2025-05-13 Zhiqiang Wang , Ruoxi Cheng

Watermarking plays a key role in the provenance and detection of AI-generated content. While existing methods prioritize robustness against real-world distortions (e.g., JPEG compression and noise addition), we reveal a fundamental…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Zhongjie Ba , Yitao Zhang , Peng Cheng , Bin Gong , Xinyu Zhang , Qinglong Wang , Kui Ren

Tree-Ring Watermarking is a significant technique for authenticating AI-generated images. However, its effectiveness in rectified flow-based models remains unexplored, particularly given the inherent challenges of these models with noise…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Ved Umrajkar , Aakash Kumar Singh

Large Language Models (LLMs) perform impressively well in various applications. However, the potential for misuse of these models in activities such as plagiarism, generating fake news, and spamming has raised concern about their…

Computation and Language · Computer Science 2025-01-20 Vinu Sankar Sadasivan , Aounon Kumar , Sriram Balasubramanian , Wenxiao Wang , Soheil Feizi

Recently, text watermarking algorithms for large language models (LLMs) have been proposed to mitigate the potential harms of text generated by LLMs, including fake news and copyright issues. However, current watermark detection algorithms…

Computation and Language · Computer Science 2024-05-28 Aiwei Liu , Leyi Pan , Xuming Hu , Shu'ang Li , Lijie Wen , Irwin King , Philip S. Yu

Large pre-trained language models (PLMs) have proven to be a crucial component of modern natural language processing systems. PLMs typically need to be fine-tuned on task-specific downstream datasets, which makes it hard to claim the…

Computation and Language · Computer Science 2023-02-13 Chenxi Gu , Chengsong Huang , Xiaoqing Zheng , Kai-Wei Chang , Cho-Jui Hsieh

Text watermarks in large language models (LLMs) are increasingly used to detect synthetic text, mitigating misuse cases like fake news and academic dishonesty. While existing watermarking detection techniques primarily focus on classifying…

Computation and Language · Computer Science 2025-06-13 Xuandong Zhao , Chenwen Liao , Yu-Xiang Wang , Lei Li

The advent of large language models (LLMs) has revolutionized the field of text generation, producing outputs that closely mimic human-like writing. Although academic and industrial institutions have developed detectors to prevent the…

Machine Learning · Computer Science 2025-02-25 Tianchun Wang , Yuanzhou Chen , Zichuan Liu , Zhanwen Chen , Haifeng Chen , Xiang Zhang , Wei Cheng

As large language models (LLMs) become increasingly deployed in safety-critical applications, the lack of systematic methods to assess their vulnerability to jailbreak attacks presents a critical security gap. We introduce the jailbreak…

Cryptography and Security · Computer Science 2026-04-27 Shuyi Lin , Anshuman Suri , Alina Oprea , Cheng Tan
‹ Prev 1 8 9 10 Next ›