English
Related papers

Related papers: Mitigating Adversarial Attacks in LLMs through Def…

200 papers

With the advancement of Large Language Models (LLMs), significant progress has been made in code generation, enabling LLMs to transform natural language into programming code. These Code LLMs have been widely accepted by massive users and…

Cryptography and Security · Computer Science 2023-12-14 Fangzhou Wu , Xiaogeng Liu , Chaowei Xiao

Beyond simple text generation, Large Language Models (LLMs) have evolved into agentic systems capable of planning and interacting with external tools to solve complex tasks. This evolution involves fine-tuning LLMs on agent-specific tasks…

Computation and Language · Computer Science 2025-11-18 Dongyoon Hahm , Taywon Min , Woogyeol Jin , Kimin Lee

Context: Large Language Models (LLMs) rely on static, pre-deployment safety mechanisms that cannot adapt to adversarial threats discovered after release. Objective: To design a software architecture enabling LLM-based systems to…

Software Engineering · Computer Science 2026-04-03 Tyler Slater

Large Language Models (LLMs) are becoming vital tools that help us solve and understand complex problems by acting as digital assistants. LLMs can generate convincing explanations, even when only given the inputs and outputs of these…

Computation and Language · Computer Science 2024-10-14 Rohan Ajwani , Shashidhar Reddy Javaji , Frank Rudzicz , Zining Zhu

As Large Language Models (LLMs) increasingly become key components in various AI applications, understanding their security vulnerabilities and the effectiveness of defense mechanisms is crucial. This survey examines the security challenges…

Machine Learning · Computer Science 2024-06-04 Frank Weizhen Liu , Chenhui Hu

Augmenting toxic language data in a controllable and class-specific manner is crucial for improving robustness in toxicity classification, yet remains challenging due to limited supervision and distributional skew. We propose ToxiGAN, a…

Computation and Language · Computer Science 2026-01-07 Peiran Li , Jan Fillies , Adrian Paschke

Large Language Models (LLMs) have raised increasing concerns about their misuse in generating hate speech. Among all the efforts to address this issue, hate speech detectors play a crucial role. However, the effectiveness of different…

Cryptography and Security · Computer Science 2025-01-29 Xinyue Shen , Yixin Wu , Yiting Qu , Michael Backes , Savvas Zannettou , Yang Zhang

The stability of recursively trained large language models (LLMs) is a foundational problem for AI safety. Prevailing theory predicts model collapse, a progressive degradation when models are trained on their own output. We challenge this…

Machine Learning · Computer Science 2025-09-16 Sai Teja Reddy Adapala

As large language models (LLMs) scale, their inference incurs substantial computational resources, exposing them to energy-latency attacks, where crafted prompts induce high energy and latency cost. Existing attack methods aim to prolong…

Cryptography and Security · Computer Science 2025-11-12 Xingyu Li , Xiaolei Liu , Cheng Liu , Yixiao Xu , Kangyi Ding , Bangzhou Xin , Jia-Li Yin

Gradient-based adversarial prompting, such as the Greedy Coordinate Gradient (GCG) algorithm, has emerged as a powerful method for jailbreaking large language models (LLMs). In this paper, we present a systematic appraisal of GCG and its…

Computation and Language · Computer Science 2025-09-03 Yuting Tan , Xuying Li , Zhuo Li , Huizhen Shu , Peikang Hu

Large language models (LLMs) have seen significant advancements, achieving superior performance in various Natural Language Processing (NLP) tasks, from understanding to reasoning. However, they remain vulnerable to backdoor attacks, where…

Computation and Language · Computer Science 2024-11-28 Chen Chen , Yuchen Sun , Xueluan Gong , Jiaxin Gao , Kwok-Yan Lam

With the advancement of technology, large language models (LLMs) have achieved remarkable performance across various natural language processing (NLP) tasks, powering LLM-integrated applications like Microsoft Copilot. However, as LLMs…

Cryptography and Security · Computer Science 2025-08-05 Yulin Chen , Haoran Li , Zihao Zheng , Yangqiu Song , Dekai Wu , Bryan Hooi

Rebuttal generation is a critical component of the peer review process for scientific papers, enabling authors to clarify misunderstandings, correct factual inaccuracies, and guide reviewers toward a more accurate evaluation. We observe…

Artificial Intelligence · Computer Science 2026-03-31 Jyotsana Khatri , Manasi Patwardhan

While most LLMs are autoregressive, diffusion-based LLMs have recently emerged as an alternative method for generation. Greedy Coordinate Gradient (GCG) attacks have proven effective against autoregressive models, but their applicability to…

Machine Learning · Computer Science 2026-01-22 Ruben Neyroud , Sam Corley

Adversarial factuality refers to the deliberate insertion of misinformation into input prompts by an adversary, characterized by varying levels of expressed confidence. In this study, we systematically evaluate the performance of several…

Computation and Language · Computer Science 2025-03-17 Shahnewaz Karim Sakib , Anindya Bijoy Das , Shibbir Ahmed

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse applications, yet they pose significant security risks that threaten their safe deployment in critical domains. Current security alignment methodologies…

Cryptography and Security · Computer Science 2025-07-22 Pengfei Du

The increasing deployment of large language models (LLMs) in safety-critical applications raises fundamental challenges in systematically evaluating robustness against adversarial behaviors. Existing red-teaming practices are largely manual…

Human motion generation driven by deep generative models has enabled compelling applications, but the ability of text-to-motion (T2M) models to produce realistic motions from text prompts raises security concerns if exploited maliciously.…

Computer Vision and Pattern Recognition · Computer Science 2024-08-02 Honglei Miao , Fan Ma , Ruijie Quan , Kun Zhan , Yi Yang

Neural networks are vulnerable to adversarially-constructed perturbations of their inputs. Most research so far has considered perturbations of a fixed magnitude under some $l_p$ norm. Although studying these attacks is valuable, there has…

Machine Learning · Computer Science 2019-10-02 Isaac Dunn , Hadrien Pouget , Tom Melham , Daniel Kroening

Recent defenses for safeguarding open-weight large language models (LLMs) are intended to prevent adversarial usage. Underlying these defenses is an assumption that new harmful behavior is learned through fine-tuning rather than elicited by…

Machine Learning · Computer Science 2026-05-27 Kevin Kuo , Chhavi Yadav , Virginia Smith