English
Related papers

Related papers: Does Representation Intervention Really Identify D…

200 papers

Recent Large Vision Language Models (LVLMs) present remarkable zero-shot conversational and reasoning capabilities given multimodal queries. Nevertheless, they suffer from object hallucination, a phenomenon where LVLMs are prone to generate…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Yun Xing , Yiheng Li , Ivan Laptev , Shijian Lu

Large language models (LLMs) trained on webscale data can produce toxic outputs, raising concerns for safe deployment. Prior defenses, based on applications of DPO, NPO, and similar algorithms, reduce the likelihood of harmful…

While neural symbolic methods demonstrate impressive performance in visual question answering on synthetic images, their performance suffers on real images. We identify that the long-tail distribution of visual concepts and unequal…

Computer Vision and Pattern Recognition · Computer Science 2021-10-04 Zhuowan Li , Elias Stengel-Eskin , Yixiao Zhang , Cihang Xie , Quan Tran , Benjamin Van Durme , Alan Yuille

Although Large Reasoning Models (LRMs) have progressed in solving complex problems, their chain-of-thought (CoT) reasoning often contains harmful content that can persist even when the final responses appear safe. We show that this issue…

Artificial Intelligence · Computer Science 2026-03-03 Yichi Zhang , Yue Ding , Jingwen Yang , Tianwei Luo , Dongbai Li , Ranjie Duan , Qiang Liu , Hang Su , Yinpeng Dong , Jun Zhu

Large Vision-Language Models (LVLMs) are vulnerable to a growing array of multimodal jailbreak attacks, necessitating defenses that are both generalizable to novel threats and efficient for practical deployment. Many current strategies fall…

Cryptography and Security · Computer Science 2026-04-21 Peichun Hua , Hao Li , Shanghao Shi , Zhiyuan Yu , Ning Zhang

Backdoor attacks pose a serious threat to deep learning models by allowing adversaries to implant hidden behaviors that remain dormant on clean inputs but are maliciously triggered at inference. Existing backdoor attack methods typically…

Cryptography and Security · Computer Science 2025-11-18 Lijie Hu , Junchi Liao , Weimin Lyu , Shaopeng Fu , Tianhao Huang , Shu Yang , Guimin Hu , Di Wang

With the increasing adoption of Large Language Models (LLMs), more customization is needed to ensure privacy-preserving and safe generation. We address this objective from two critical aspects: unlearning of sensitive information and…

Machine Learning · Computer Science 2025-10-17 Fatmazohra Rezkellah , Ramzi Dakhmouche

Large language models (LLMs) are susceptible to a type of attack known as jailbreaking, which misleads LLMs to output harmful contents. Although there are diverse jailbreak attack strategies, there is no unified understanding on why some…

Computation and Language · Computer Science 2024-12-04 Yuping Lin , Pengfei He , Han Xu , Yue Xing , Makoto Yamada , Hui Liu , Jiliang Tang

Large Language Models are susceptible to jailbreak attacks that bypass built-in safety guardrails (e.g., by tricking the model with adversarial prompts). We propose Concept Alignment and Concept Manipulation CALM, an inference-time method…

Machine Learning · Computer Science 2025-10-20 Ruben Belo , Marta Guimaraes , Claudia Soares

Large Language Models (LLMs) increasingly employ alignment techniques to prevent harmful outputs. Despite these safeguards, attackers can circumvent them by crafting prompts that induce LLMs to generate harmful content. Current methods…

Computation and Language · Computer Science 2025-10-21 Jiawei Lian , Jianhong Pan , Lefan Wang , Yi Wang , Shaohui Mei , Lap-Pui Chau

Robust alignment guardrails for large language models (LLMs) are becoming increasingly important with their widespread application. In contrast to previous studies, we demonstrate that inference-time activation interventions can bypass…

Computation and Language · Computer Science 2025-08-26 Paul Darm , Annalisa Riccardi

Concept bottleneck models (CBMs) are a class of interpretable neural network models that predict the target response of a given input based on its high-level concepts. Unlike the standard end-to-end models, CBMs enable domain experts to…

Machine Learning · Computer Science 2023-07-04 Sungbin Shin , Yohan Jo , Sungsoo Ahn , Namhoon Lee

Interpreting the internal reasoning of vision-language models is essential for deploying AI in safety-critical domains. Concept-based explainability provides a human-aligned lens by representing a model's behavior through semantically…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Ehud Gordon , Meir Yossef Levi , Guy Gilboa

Recent work in interpretability shows that large language models (LLMs) can be adapted for new tasks in a learning-free way: it is possible to intervene on LLM representations to elicit desired behaviors for alignment. For instance, adding…

Computation and Language · Computer Science 2024-11-01 Fangcong Yin , Xi Ye , Greg Durrett

Large Language Models (LLMs) have catalyzed transformative advances across a spectrum of natural language processing tasks through few-shot or zero-shot prompting, bypassing the need for parameter tuning. While convenient, this modus…

Artificial Intelligence · Computer Science 2024-03-12 Zhen Tan , Jie Peng , Tianlong Chen , Huan Liu

Reasoning-enhanced large language models (LLMs) explicitly generate intermediate reasoning steps prior to generating final answers, helping the model excel in complex problem-solving. In this paper, we demonstrate that this emerging…

Machine Learning · Computer Science 2025-05-22 Tong Wu , Chong Xiang , Jiachen T. Wang , G. Edward Suh , Prateek Mittal

Intent-obfuscation-based jailbreak attacks on multimodal large language models (MLLMs) transform a harmful query into a concealed multimodal input to bypass safety mechanisms. We show that such attacks are governed by a…

Artificial Intelligence · Computer Science 2026-05-08 Md Farhamdur Reza , Richeng Jin , Tianfu Wu , Huaiyu Dai

Learning a set of tasks over time, also known as continual learning (CL), is one of the most challenging problems in artificial intelligence due to catastrophic forgetting. Large language models (LLMs) are often impractical to frequent…

Machine Learning · Computer Science 2025-10-28 Jaya Krishna Mandivarapu

The honesty of large language models (LLMs) is a critical alignment challenge, especially as advanced systems with chain-of-thought (CoT) reasoning may strategically deceive humans. Unlike traditional honesty issues on LLMs, which could be…

Artificial Intelligence · Computer Science 2025-06-06 Kai Wang , Yihao Zhang , Meng Sun

Defending large language models (LLMs) against jailbreak attacks is essential for their safe and reliable deployment. Existing defenses often rely on shallow pattern matching, which struggles to generalize to novel and unseen attack…

Artificial Intelligence · Computer Science 2025-08-06 Rui Pu , Chaozhuo Li , Rui Ha , Litian Zhang , Lirong Qiu , Xi Zhang