English
Related papers

Related papers: Automated Progressive Red Teaming

200 papers

Large language models (LLMs) are susceptible to social-engineered attacks that are human-interpretable but require a high level of comprehension for LLMs to counteract. Existing defensive measures can only mitigate less than half of these…

Computation and Language · Computer Science 2025-05-01 Canaan Yung , Hadi Mohaghegh Dolatabadi , Sarah Erfani , Christopher Leckie

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We…

Machine Learning · Computer Science 2025-06-23 Tianle Gu , Kexin Huang , Zongqi Wang , Yixu Wang , Jie Li , Yuanqi Yao , Yang Yao , Yujiu Yang , Yan Teng , Yingchun Wang

Prompt-based learning is a new language model training paradigm that adapts the Pre-trained Language Models (PLMs) to downstream tasks, which revitalizes the performance benchmarks across various natural language processing (NLP) tasks.…

Computation and Language · Computer Science 2024-04-10 Yue Xu , Wenjie Wang

With the rapid evolution of Android applications, traditional machine learning-based detection models suffer from concept drift. Additionally, they are constrained by shallow features, lacking deep semantic understanding and…

Cryptography and Security · Computer Science 2026-04-29 Xueying Zeng , Youquan Xian , Sihao Liu , Xudong Mou , Yanze Li , Lei Cui , Bo Li

This technical report accompanies the LLM robustness leaderboard published by PRISM Eval for the Paris AI Action Summit. We introduce PRISM Eval Behavior Elicitation Tool (BET), an AI system performing automated red-teaming through Dynamic…

Artificial Intelligence · Computer Science 2025-08-14 Pierre Peigné - Lefebvre , Quentin Feuillade-Montixi , Tom David , Nicolas Miailhe

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by retrieving relevant documents from external sources to improve factual accuracy and verifiability. However, this reliance introduces new attack surfaces within…

Computer Vision and Pattern Recognition · Computer Science 2025-09-19 Saket S. Chaturvedi , Gaurav Bagwe , Lan Zhang , Xiaoyong Yuan

Visuomotor policies trained via imitation learning are capable of performing challenging manipulation tasks, but are often extremely brittle to lighting, visual distractors, and object locations. These vulnerabilities can depend…

This paper analyzes Large Language Model (LLM) security vulnerabilities based on data from Crucible, encompassing 214,271 attack attempts by 1,674 users across 30 LLM challenges. Our findings reveal automated approaches significantly…

Cryptography and Security · Computer Science 2025-04-30 Rob Mulla , Ads Dawson , Vincent Abruzzon , Brian Greunke , Nick Landers , Brad Palm , Will Pearce

Advanced Persistent Threats (APTs) pose a major cybersecurity challenge due to their stealth and ability to mimic normal system behavior, making detection particularly difficult in highly imbalanced datasets. Traditional anomaly detection…

Cryptography and Security · Computer Science 2025-02-14 Sidahmed Benabderrahmane , Petko Valtchev , James Cheney , Talal Rahwan

Large Language Models (LLMs) are increasingly applied to tasks involving structured inputs such as graphs. Abstract Meaning Representations (AMRs), which encode rich semantics as directed graphs, offer a rigorous testbed for evaluating LLMs…

Computation and Language · Computer Science 2025-12-11 Rafiq Kamel , Filippo Guerranti , Simon Geisler , Stephan Günnemann

Retrieval-Augmented Generation (RAG) systems for Large Language Models (LLMs) hold promise in knowledge-intensive tasks but face limitations in complex multi-step reasoning. While recent methods have integrated RAG with chain-of-thought…

Computation and Language · Computer Science 2025-01-15 Zhongxiang Sun , Qipeng Wang , Weijie Yu , Xiaoxue Zang , Kai Zheng , Jun Xu , Xiao Zhang , Song Yang , Han Li

Large language models (LLMs) demonstrate strong performance in math reasoning benchmarks, but their performance varies inconsistently across problems with varying levels of difficulty. This paper describes Adaptive Multi-Expert Reasoning…

Computation and Language · Computer Science 2026-04-14 Mohamed Ehab , Ali Hamdi

Automated Program Repair (APR) aims to help developers automatically patch software bugs. However, current state-of-the-art traditional and learning-based APR techniques face the problem of limited patch variety, failing to fix complicated…

Software Engineering · Computer Science 2024-12-11 Chunqiu Steven Xia , Yuxiang Wei , Lingming Zhang

Adversarial attacks pose a significant threat to the reliability of pre-trained language models (PLMs) such as GPT, BERT, RoBERTa, and T5. This paper presents Adversarial Robustness through Dynamic Ensemble Learning (ARDEL), a novel scheme…

Cryptography and Security · Computer Science 2025-05-14 Hetvi Waghela , Jaydip Sen , Sneha Rakshit

Large language models (LLMs) remain vulnerable to sophisticated prompt engineering attacks that exploit contextual framing to bypass safety mechanisms, posing significant risks in cybersecurity applications. We introduce Jailbreak Mimicry,…

Cryptography and Security · Computer Science 2025-10-28 Pavlos Ntais

Process Reward Models (PRMs) enhance reasoning ability of LLMs by providing step-level supervision. However, their widespread adoption is limited due to expensive manual step-level annotation and poor generalization of static training data…

Machine Learning · Computer Science 2025-12-01 Gurusha Juneja , Deepak Nathani , William Yang Wang

We utilise the power of Large Language Models (LLMs), in particular GPT4, to be prompt engineered into performing an arbitrary task. Here, we give the model some human priors via text, along with some typical procedures for solving the ARC…

Artificial Intelligence · Computer Science 2023-06-07 Tan John Chong Min

Large Language Models (LLMs) have been augmented with web search to overcome the limitations of the static knowledge boundary by accessing up-to-date information from the open Internet. While this integration enhances model capability, it…

Cryptography and Security · Computer Science 2026-04-20 Haoran Ou , Kangjie Chen , Xingshuo Han , Gelei Deng , Jie Zhang , Han Qiu , Tianwei Zhang

Advanced Persistent Threats (APTs) represent a growing menace to modern digital infrastructure. Unlike traditional cyberattacks, APTs are stealthy, adaptive, and long-lasting, often bypassing signature-based detection systems. This paper…

Cryptography and Security · Computer Science 2025-08-27 Sidahmed Benabderrahmane , Talal Rahwan

Traditional benchmarks for large language models (LLMs), such as HELM and AIR-BENCH, primarily assess safety through breadth-oriented evaluation across diverse tasks and risk categories. However, real-world deployment often exposes a…

Machine Learning · Computer Science 2026-04-29 Keita Broadwater
‹ Prev 1 4 5 6 7 8 10 Next ›