English
Related papers

Related papers: Before the Last Token: Diagnosing Final-Token Safe…

200 papers

Large language models are increasingly deployed in safety-critical applications, where their ability to resist harmful instructions is essential. Although post-training aims to make models robust against many jailbreak strategies, recent…

We present InvThink, a training and prompting framework that requires the model to enumerate, analyze, and constrain potential failures before generating its final response. Unlike existing safety alignment methods that optimize only for…

Artificial Intelligence · Computer Science 2026-05-11 Yubin Kim , Taehan Kim , Eugene Park , Chunjong Park , Cynthia Breazeal , Daniel McDuff , Hae Won Park

Large language models (LLMs) are increasingly applied in specialized domains such as finance and healthcare, where they introduce unique safety risks. Domain-specific datasets of harmful prompts remain scarce and still largely rely on…

Computation and Language · Computer Science 2026-04-21 Huawei Zheng , Xinqi Jiang , Sen Yang , Shouling Ji , Yingcai Wu , Dazhen Deng

Large Language Models (LLMs) face increasing threats from jailbreak attacks that bypass safety alignment. While prompt-based defenses such as Role-Oriented Prompts (RoP) and Task-Oriented Prompts (ToP) have shown effectiveness, the role of…

Computation and Language · Computer Science 2026-02-05 Yanshu Wang , Shuaishuai Yang , Jingjing He , Tong Yang

Large language models (LLMs) have achieved unprecedented success in the field of natural language processing. However, the black-box nature of their internal mechanisms has brought many concerns about their trustworthiness and…

Computation and Language · Computer Science 2024-09-24 Zhibo Zhang , Wuxia Bai , Yuxi Li , Mark Huasong Meng , Kailong Wang , Ling Shi , Li Li , Jun Wang , Haoyu Wang

Speech-driven large language models (LLMs) are increasingly accessed through speech interfaces, introducing new security risks via open acoustic channels. We present Sirens' Whisper (SWhisper), the first practical framework for covert…

Cryptography and Security · Computer Science 2026-03-17 Zijian Ling , Pingyi Hu , Xiuyong Gao , Xiaojing Ma , Man Zhou , Jun Feng , Songfeng Lu , Dongmei Zhang , Bin Benjamin Zhu

Large Language Models (LLMs), especially their compact efficiency-oriented variants, remain susceptible to jailbreak attacks that can elicit harmful outputs despite extensive alignment efforts. Existing adversarial prompt generation…

Current jailbreaking work on large language models (LLMs) aims to elicit unsafe outputs from given prompts. However, it only focuses on single-turn jailbreaking targeting one specific query. On the contrary, the advanced LLMs are designed…

Computation and Language · Computer Science 2025-08-12 Xianjun Yang , Liqiang Xiao , Shiyang Li , Faisal Ladhak , Hyokun Yun , Linda Ruth Petzold , Yi Xu , William Yang Wang

While large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, they pose potential safety concerns, such as the ``jailbreak'' problem, wherein malicious instructions can manipulate LLMs to exhibit…

Computation and Language · Computer Science 2024-03-05 Yue Deng , Wenxuan Zhang , Sinno Jialin Pan , Lidong Bing

As the pre-trained language models (PLMs) continue to grow, so do the hardware and data requirements for fine-tuning PLMs. Therefore, the researchers have come up with a lighter method called \textit{Prompt Learning}. However, during the…

Computation and Language · Computer Science 2022-09-07 Yundi Shi , Piji Li , Changchun Yin , Zhaoyang Han , Lu Zhou , Zhe Liu

Activation-based probes have emerged as a promising approach for detecting deceptively aligned AI systems by identifying internal conflict between true and stated goals. We identify a fundamental blind spot: probes fail on coherent…

Machine Learning · Computer Science 2026-03-30 Kristiyan Haralambiev

This paper proposes a jailbreaking prompt detection method for large language models (LLMs) to defend against jailbreak attacks. Although recent LLMs are equipped with built-in safeguards, it remains possible to craft jailbreaking prompts…

Cryptography and Security · Computer Science 2026-05-12 Zheng Lin , Zhenxing Niu , Haoxuan Ji , Yuzhe Huang , Haichang Gao

Large language models (LLMs) are increasingly deployed in security-sensitive applications, where they must follow system- or developer-specified instructions that define the intended task behavior, while completing benign user requests.…

Cryptography and Security · Computer Science 2026-01-13 Shawn Li , Chenxiao Yu , Zhiyu Ni , Hao Li , Charith Peris , Chaowei Xiao , Yue Zhao

Visual prompting (VP) is a new technique that adapts well-trained frozen models for source domain tasks to target domain tasks. This study examines VP's benefits for black-box model-level backdoor detection. The visual prompt in VP maps…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Zi-Xuan Huang , Jia-Wei Chen , Zhi-Peng Zhang , Chia-Mu Yu

Multimodal large language models (MLLMs) have become integral to a wide range of real-world applications by jointly reasoning over text and visual inputs. However, despite recent advances in safety alignment, MLLMs remain vulnerable to…

Cryptography and Security · Computer Science 2026-03-10 Xinkai Wang , Beibei Li , Zerui Shao , Ao Liu , Guangquan Xu , Shouling Ji

Although safely enhanced Large Language Models (LLMs) have achieved remarkable success in tackling various complex tasks in a zero-shot manner, they remain susceptible to jailbreak attacks, particularly the unknown jailbreak attack. To…

Computation and Language · Computer Science 2024-06-12 Fan Liu , Zhao Xu , Hao Liu

The pre-training of large language models (LLMs) relies on massive text datasets sourced from diverse and difficult-to-curate origins. Although membership inference attacks and hidden canaries have been explored to trace data usage, such…

Cryptography and Security · Computer Science 2025-06-19 Wassim Bouaziz , Mathurin Videau , Nicolas Usunier , El-Mahdi El-Mhamdi

Instruction fine-tuning attacks pose a serious threat to large language models (LLMs) by subtly embedding poisoned examples in fine-tuning datasets, leading to harmful or unintended behaviors in downstream applications. Detecting such…

Machine Learning · Computer Science 2026-02-02 Jiawei Li

Large language models (LLMs) increasingly rely on chain-of-thought (CoT) prompting to solve mathematical and logical reasoning tasks. Yet, a central question remains: to what extent are these generated rationales \emph{faithful} to the…

Computation and Language · Computer Science 2025-10-15 Arash Marioriyad , Shaygan Adim , Nima Alighardashi , Mahdieh Soleymani Banghshah , Mohammad Hossein Rohban

Large-scale pre-trained models are increasingly adapted to downstream tasks through a new paradigm called prompt learning. In contrast to fine-tuning, prompt learning does not update the pre-trained model's parameters. Instead, it only…

Cryptography and Security · Computer Science 2023-10-19 Yixin Wu , Rui Wen , Michael Backes , Pascal Berrang , Mathias Humbert , Yun Shen , Yang Zhang