English
Related papers

Related papers: BadGPT-4o: stripping safety finetuning from GPT mo…

200 papers

The demand of customized large language models (LLMs) has led to commercial LLMs offering black-box fine-tuning APIs, yet this convenience introduces a critical security loophole: attackers could jailbreak the LLMs by fine-tuning them with…

Cryptography and Security · Computer Science 2026-01-21 Zhixin Xie , Xurui Song , Jun Luo

Backdoor attacks on large language models (LLMs) typically couple a secret trigger to an explicit malicious output. We show that this explicit association is unnecessary for common LLMs. We introduce a compliance-only backdoor: supervised…

Machine Learning · Computer Science 2025-11-18 Yuting Tan , Yi Huang , Zhuo Li

Jailbreak attacks reveal critical vulnerabilities in Large Language Models (LLMs) by causing them to generate harmful or unethical content. Evaluating these threats is particularly challenging due to the evolving nature of LLMs and the…

Machine Learning · Computer Science 2025-07-11 Peiyan Zhang , Haibo Jin , Liying Kang , Haohan Wang

Backdoor attacks poison the training data, causing the model to behave normally on clean inputs but predict attacker-chosen labels when trigger patterns are embedded into the input samples. Defending against such attacks is highly…

Cryptography and Security · Computer Science 2026-04-28 Wei Guo , Maura Pintor , Ambra Demontis , Battista Biggio

This paper investigates the impact of model compression on the way Large Language Models (LLMs) process prompts, particularly concerning jailbreak resistance. We show that moderate WANDA pruning can enhance resistance to jailbreaking…

Machine Learning · Computer Science 2024-11-01 Adib Hasan , Ileana Rugina , Alex Wang

While Large Language Models (LLMs) have achieved remarkable progress, they remain vulnerable to jailbreak attacks. Existing methods, primarily relying on discrete input optimization (e.g., GCG), often suffer from high computational costs…

Computation and Language · Computer Science 2026-01-09 Wenpeng Xing , Mohan Li , Chunqiang Hu , Haitao Xu , Ningyu Zhang , Bo Lin , Meng Han

With the significant advancement of Large Vision-Language Models (VLMs), concerns about their potential misuse and abuse have grown rapidly. Previous studies have highlighted VLMs' vulnerability to jailbreak attacks, where carefully crafted…

Computer Vision and Pattern Recognition · Computer Science 2025-06-19 Yu Wang , Xiaofei Zhou , Yichen Wang , Geyuan Zhang , Tianxing He

Small Language Models (SLMs) are emerging as efficient and economically viable alternatives to Large Language Models (LLMs), offering competitive performance with significantly lower computational costs and latency. These advantages make…

Cryptography and Security · Computer Science 2026-04-01 Md Jueal Mia , Joaquin Molto , Yanzhao Wu , M. Hadi Amini

Language model attacks typically assume one of two extreme threat models: full white-box access to model weights, or black-box access limited to a text generation API. However, real-world APIs are often more flexible than just text…

Cryptography and Security · Computer Science 2024-08-06 Kellin Pelrine , Mohammad Taufeeque , Michał Zając , Euan McLean , Adam Gleave

Machine learning models are vulnerable to data-poisoning attacks, in which an attacker maliciously modifies the training set to change the prediction of a learned model. In a trigger-less attack, the attacker can modify the training set but…

Machine Learning · Computer Science 2022-10-18 Yuhao Zhang , Aws Albarghouthi , Loris D'Antoni

Large Language Models (LLMs) have excelled in various tasks but are still vulnerable to jailbreaking attacks, where attackers create jailbreak prompts to mislead the model to produce harmful or offensive content. Current jailbreak methods…

Cryptography and Security · Computer Science 2025-03-04 Xueluan Gong , Mingzhe Li , Yilin Zhang , Fengyuan Ran , Chen Chen , Yanjiao Chen , Qian Wang , Kwok-Yan Lam

Various jailbreak attacks have been proposed to red-team Large Language Models (LLMs) and revealed the vulnerable safeguards of LLMs. Besides, some methods are not limited to the textual modality and extend the jailbreak attack to…

Machine Learning · Computer Science 2024-12-17 Shuo Chen , Zhen Han , Bailan He , Zifeng Ding , Wenqian Yu , Philip Torr , Volker Tresp , Jindong Gu

Large language models (LLMs) have exhibited outstanding performance in engaging with humans and addressing complex questions by leveraging their vast implicit knowledge and robust reasoning capabilities. However, such models are vulnerable…

Computation and Language · Computer Science 2024-10-16 Hao Yang , Lizhen Qu , Ehsan Shareghi , Gholamreza Haffari

As large language models (LLMs) become more powerful and are deployed more autonomously, it will be increasingly important to prevent them from causing harmful outcomes. Researchers have investigated a variety of safety techniques for this…

Machine Learning · Computer Science 2024-07-24 Ryan Greenblatt , Buck Shlegeris , Kshitij Sachan , Fabien Roger

By incorporating visual inputs, Multimodal Large Language Models (MLLMs) extend LLMs to support visual reasoning. However, this integration also introduces new vulnerabilities, making MLLMs susceptible to multimodal jailbreak attacks and…

Cryptography and Security · Computer Science 2025-12-04 Beitao Chen , Xinyu Lyu , Lianli Gao , Jingkuan Song , Heng Tao Shen

Jailbreak attacks bypass the guardrails of large language models to produce harmful outputs. In this paper, we ask whether the model outputs produced by existing jailbreaks are actually useful. For example, when jailbreaking a model to give…

Machine Learning · Computer Science 2025-04-16 Kristina Nikolić , Luze Sun , Jie Zhang , Florian Tramèr

Multimodal Large Language Models (MLLMs) have become widely deployed, yet their safety alignment remains fragile under adversarial inputs. Previous work has shown that increasing inference steps can disrupt safety mechanisms and lead MLLMs…

Computer Vision and Pattern Recognition · Computer Science 2026-04-17 Xiangdong Hu , Yangyang Jiang , Qin Hu , Xiaojun Jia

As Large Language Models (LLMs) become integral to computing infrastructure, safety alignment serves as the primary security control preventing the generation of harmful payloads. However, this defense remains brittle. Existing jailbreak…

Cryptography and Security · Computer Science 2026-02-19 Mingrui Liu , Sixiao Zhang , Cheng Long , Kwok Yan Lam

While large language models (LLMs) such as Llama-2 or GPT-4 have shown impressive zero-shot performance, fine-tuning is still necessary to enhance their performance for customized datasets, domain-specific tasks, or other private needs.…

Machine Learning · Computer Science 2025-01-07 Chia-Yi Hsu , Yu-Lin Tsai , Chih-Hsun Lin , Pin-Yu Chen , Chia-Mu Yu , Chun-Ying Huang

It has been widely observed that deep neural networks (DNN) are vulnerable to backdoor attacks where attackers could manipulate the model behavior maliciously by tampering with a small set of training samples. Although a line of defense…

Machine Learning · Computer Science 2023-10-24 Rui Min , Zeyu Qin , Li Shen , Minhao Cheng
‹ Prev 1 3 4 5 6 7 10 Next ›