English
Related papers

Related papers: ShadowLogic: Backdoors in Any Whitebox LLM

200 papers

As large language models (LLMs) become increasingly integrated into real-world applications such as code generation and chatbot assistance, extensive efforts have been made to align LLM behavior with human values, including safety.…

Cryptography and Security · Computer Science 2024-07-29 Zhangchen Xu , Fengqing Jiang , Luyao Niu , Jinyuan Jia , Bill Yuchen Lin , Radha Poovendran

Large Transformer models are capable of implementing a plethora of so-called in-context learning algorithms. These include gradient descent, classification, sequence completion, transformation, and improvement. In this work, we investigate…

Artificial Intelligence · Computer Science 2024-02-29 Robert Tjarko Lange , Yingtao Tian , Yujin Tang

Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where the adversarial training examples are correctly labeled.…

Machine Learning · Computer Science 2023-10-31 Wencong You , Zayd Hammoudeh , Daniel Lowd

Large Language Models (LLMs) with safe-alignment training are powerful instruments with robust language comprehension capabilities. These models typically undergo meticulous alignment procedures involving human feedback to ensure the…

Machine Learning · Computer Science 2025-09-22 Maithili Joshi , Palash Nandi , Tanmoy Chakraborty

Vision-Language Models (VLMs) are increasingly deployed in consumer applications where users seek recommendations about products, dining, and services. We introduce Hidden Ads, a new class of backdoor attacks that exploit this…

Computation and Language · Computer Science 2026-03-31 Duanyi Yao , Changyue Li , Zhicong Huang , Cheng Hong , Songze Li

Large language models have gained widespread prominence, yet their vulnerability to prompt injection and other adversarial attacks remains a critical concern. This paper argues for a security-by-design AI paradigm that proactively mitigates…

Cryptography and Security · Computer Science 2025-10-02 Dalal Alharthi , Ivan Roberto Kawaminami Garcia

The evolution of Generative AI and the capabilities of the newly released Large Language Models (LLMs) open new opportunities in software engineering. However, they also lead to new challenges in cybersecurity. Recently, researchers have…

Cryptography and Security · Computer Science 2023-09-08 Mika Beckerich , Laura Plein , Sergio Coronado

Large Language Models (LLMs) deployed in enterprise settings (e.g., as Microsoft 365 Copilot) face novel security challenges. One critical threat is prompt inference attacks: adversaries chain together seemingly benign prompts to gradually…

Cryptography and Security · Computer Science 2025-07-22 Andrii Balashov , Olena Ponomarova , Xiaohua Zhai

Early backdoor attacks against machine learning set off an arms race in attack and defence development. Defences have since appeared demonstrating some ability to detect backdoors in models or even remove them. These defences work by…

Machine Learning · Computer Science 2024-06-03 Eleanor Clifford , Ilia Shumailov , Yiren Zhao , Ross Anderson , Robert Mullins

The emergence of Vision Language Models (VLMs) is a significant advancement in integrating computer vision with Large Language Models (LLMs) to produce detailed text descriptions based on visual inputs, yet it introduces new security…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Weimin Lyu , Lu Pang , Tengfei Ma , Haibin Ling , Chao Chen

With rapid advances, generative large language models (LLMs) dominate various Natural Language Processing (NLP) tasks from understanding to reasoning. Yet, language models' inherent vulnerabilities may be exacerbated due to increased…

Cryptography and Security · Computer Science 2024-12-17 Haoran Li , Yulin Chen , Zihao Zheng , Qi Hu , Chunkit Chan , Heshan Liu , Yangqiu Song

Multimodal Large Language Models (MLLMs) have showcased impressive performance in a variety of multimodal tasks. On the other hand, the integration of additional image modality may allow the malicious users to inject harmful content inside…

Cryptography and Security · Computer Science 2025-04-23 Yulin Chen , Haoran Li , Yirui Zhang , Zihao Zheng , Yangqiu Song , Bryan Hooi

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…

Cryptography and Security · Computer Science 2025-09-09 Youjia Zheng , Mohammad Zandsalimy , Shanu Sushmita

As Large Language Models (LLMs) become increasingly integrated into software development workflows, they also become prime targets for adversarial attacks. Among these, backdoor attacks are a significant threat, allowing attackers to…

Software Engineering · Computer Science 2025-10-17 Quoc Hung Le , Thanh Le-Cong , Bach Le , Bowen Xu

Large Language Models (LLMs) are trained with safety alignment to prevent generating malicious content. Although some attacks have highlighted vulnerabilities in these safety-aligned LLMs, they typically have limitations, such as…

Machine Learning · Computer Science 2026-03-11 Jesson Wang , Zhanhao Hu , David Wagner

Ensuring the safety and alignment of large language models (LLMs) with human values is crucial for generating responses that are beneficial to humanity. While LLMs have the capability to identify and avoid harmful queries, they remain…

Computation and Language · Computer Science 2024-10-22 Yihua Zhou , Xiaochuan Shi

Chain-of-Thought (CoT) enhances an LLM's ability to perform complex reasoning tasks, but it also introduces new security issues. In this work, we present ShadowCoT, a novel backdoor attack framework that targets the internal reasoning…

Cryptography and Security · Computer Science 2026-04-23 Gejian Zhao , Hanzhou Wu , Xinpeng Zhang , Athanasios V. Vasilakos

The strong planning and reasoning capabilities of Large Language Models (LLMs) have fostered the development of agent-based systems capable of leveraging external tools and interacting with increasingly complex environments. However, these…

Cryptography and Security · Computer Science 2025-06-17 Zhun Wang , Vincent Siu , Zhe Ye , Tianneng Shi , Yuzhou Nie , Xuandong Zhao , Chenguang Wang , Wenbo Guo , Dawn Song

Although Deep Neural Network (DNN) has led to unprecedented progress in various natural language processing (NLP) tasks, research shows that deep models are extremely vulnerable to backdoor attacks. The existing backdoor attacks mainly…

Cryptography and Security · Computer Science 2022-06-07 Xiaoyi Chen , Yinpeng Dong , Zeyu Sun , Shengfang Zhai , Qingni Shen , Zhonghai Wu

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

Computation and Language · Computer Science 2025-08-29 Chen Chen , Yuchen Sun , Jiaxin Gao , Xueluan Gong , Qian Wang , Ziyao Wang , Yongsen Zheng , Kwok-Yan Lam
‹ Prev 1 8 9 10 Next ›