English
Related papers

Related papers: TrapSuffix: Proactive Defense Against Adversarial …

200 papers

Jailbreaking attacks can effectively manipulate open-source large language models (LLMs) to produce harmful responses. However, these attacks exhibit limited transferability, failing to disrupt proprietary LLMs consistently. To reliably…

Machine Learning · Computer Science 2025-05-20 Runqi Lin , Bo Han , Fengwang Li , Tongling Liu

Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains. However, their potential to generate harmful responses has raised significant societal and regulatory concerns, especially when manipulated by…

Cryptography and Security · Computer Science 2025-06-17 Advait Yadav , Haibo Jin , Man Luo , Jun Zhuang , Haohan Wang

Current LLM safety defenses fail under decomposition attacks, where a malicious goal is decomposed into benign subtasks that circumvent refusals. The challenge lies in the existing shallow safety alignment techniques: they only detect harm…

Cryptography and Security · Computer Science 2025-06-17 Chen Yueh-Han , Nitish Joshi , Yulin Chen , Maksym Andriushchenko , Rico Angell , He He

Language models (LMs) are often used as zero-shot or few-shot classifiers by scoring label words, but they remain fragile to adversarial prompts. Prior work typically optimizes task- or model-specific triggers, making results difficult to…

Computation and Language · Computer Science 2025-12-10 Sampriti Soor , Suklav Ghosh , Arijit Sur

The generalization capabilities of Large Language Models (LLMs) have led to their widespread deployment across various applications. However, this increased adoption has introduced several security threats, notably in the forms of…

Cryptography and Security · Computer Science 2025-08-04 Francesco Panebianco , Stefano Bonfanti , Francesco Trovò , Michele Carminati

A frustratingly easy technique known as the prefilling attack has been shown to effectively circumvent the safety alignment of frontier LLMs by simply prefilling the assistant response with an affirmative prefix before decoding. In…

Cryptography and Security · Computer Science 2025-12-08 Jason Vega , Gagandeep Singh

Despite their capabilities, large foundation models (LFMs) remain susceptible to adversarial manipulation. Current defenses predominantly rely on the "locality hypothesis", suppressing isolated neurons or features. However, harmful…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Chuancheng Shi , Shangze Li , Wenjun Lu , Wenhua Wu , Cong Wang , Zifeng Cheng , Fei Shen , Tat-Seng Chua

The Suffix Array is a classic text index enabling on-line pattern matching queries via simple binary search. The main drawback of the Suffix Array is that it takes linear space in the text's length, even if the text itself is extremely…

Data Structures and Algorithms · Computer Science 2025-03-19 Davide Cenzato , Lore Depuydt , Travis Gagie , Sung-Hwan Kim , Giovanni Manzini , Francisco Olivares , Nicola Prezza

Deep neural networks (DNNs) are vulnerable to backdoor attacks. Previous works have shown it extremely challenging to unlearn the undesired backdoor behavior from the network, since the entire network can be affected by the backdoor…

Cryptography and Security · Computer Science 2022-10-13 Haotao Wang , Junyuan Hong , Aston Zhang , Jiayu Zhou , Zhangyang Wang

With the rapid advancement of large language models (LLMs), ensuring their safe use becomes increasingly critical. Fine-tuning is a widely used method for adapting models to downstream tasks, yet it is vulnerable to jailbreak attacks.…

Cryptography and Security · Computer Science 2025-10-10 Xiangfang Li , Yu Wang , Bo Li

As large language models (LLMs) become integral to various applications, ensuring both their safety and utility is paramount. Jailbreak attacks, which manipulate LLMs into generating harmful content, pose significant challenges to this…

Cryptography and Security · Computer Science 2025-02-10 Guobin Shen , Dongcheng Zhao , Yiting Dong , Xiang He , Yi Zeng

The deployment of large language models (LLMs) has raised security concerns due to their susceptibility to producing harmful or policy-violating outputs when exposed to adversarial prompts. While alignment and guardrails mitigate common…

Computation and Language · Computer Science 2026-01-23 Rishit Chugh

Despite significant advancements in alignment and content moderation, large language models (LLMs) and text-to-image (T2I) systems remain vulnerable to prompt-based attacks known as jailbreaks. Unlike traditional adversarial examples…

Computer Vision and Pattern Recognition · Computer Science 2025-07-30 Ahmed B Mustafa , Zihan Ye , Yang Lu , Michael P Pound , Shreyank N Gowda

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their susceptibility to adversarial attacks, particularly jailbreaking, poses significant safety and ethical concerns. While numerous jailbreak methods exist, many…

Cryptography and Security · Computer Science 2025-06-17 Bilal Saleh Husain

LLM-powered agents often use prompt compression to reduce inference costs, but this introduces a new security risk. Compression modules, which are optimized for efficiency rather than safety, can be manipulated by adversarial inputs,…

Cryptography and Security · Computer Science 2025-11-18 Zesen Liu , Zhixiang Zhang , Yuchong Xie , Dongdong She

While significant attention has been dedicated to exploiting weaknesses in LLMs through jailbreaking attacks, there remains a paucity of effort in defending against these attacks. We point out a pivotal factor contributing to the success of…

Computation and Language · Computer Science 2024-06-13 Zhexin Zhang , Junxiao Yang , Pei Ke , Fei Mi , Hongning Wang , Minlie Huang

As large language models (LLMs) are becoming more capable and widespread, the study of their failure cases is becoming increasingly important. Recent advances in standardizing, measuring, and scaling test-time compute suggest new…

Machine Learning · Computer Science 2025-06-26 Mahdi Sabbaghi , Paul Kassianik , George Pappas , Yaron Singer , Amin Karbasi , Hamed Hassani

With the advent and widespread deployment of Multimodal Large Language Models (MLLMs), the imperative to ensure their safety has become increasingly pronounced. However, with the integration of additional modalities, MLLMs are exposed to…

Cryptography and Security · Computer Science 2024-03-15 Yu Wang , Xiaogeng Liu , Yu Li , Muhao Chen , Chaowei Xiao

Natural language processing (NLP) models are known to be vulnerable to backdoor attacks, which poses a newly arisen threat to NLP models. Prior online backdoor defense methods for NLP models only focus on the anomalies at either the input…

Computation and Language · Computer Science 2022-10-17 Sishuo Chen , Wenkai Yang , Zhiyuan Zhang , Xiaohan Bi , Xu Sun

Security alignment enables the Large Language Model (LLM) to gain the protection against malicious queries, but various jailbreak attack methods reveal the vulnerability of this security mechanism. Previous studies have isolated LLM…

Cryptography and Security · Computer Science 2025-08-07 Xiaohu Li , Yunfeng Ning , Zepeng Bao , Mayi Xu , Jianhao Chen , Tieyun Qian