English
Related papers

Related papers: Safety Context Injection: Inference-Time Safety Al…

200 papers

Frontier artificial intelligence (AI) systems present both benefits and risks to society. Safety cases - structured arguments supported by evidence - are one way to help ensure the safe development and deployment of these systems. Yet the…

Computers and Society · Computer Science 2024-12-24 Carmen Cârlan , Francesca Gomez , Yohan Mathew , Ketana Krishna , René King , Peter Gebauer , Ben R. Smith

With the blossom of large language models (LLMs), inference efficiency becomes increasingly important. Various approximation methods are proposed to reduce the cost at inference time. Contextual Sparsity (CS) is appealing for its…

Computation and Language · Computer Science 2024-09-09 Yang Zhou , Zhuoming Chen , Zhaozhuo Xu , Victoria Lin , Beidi Chen

Large Language Models (LLMs) are susceptible to Jailbreaking attacks, which aim to extract harmful information by subtly modifying the attack query. As defense mechanisms evolve, directly obtaining harmful information becomes increasingly…

Machine Learning · Computer Science 2024-10-03 Yixin Cheng , Markos Georgopoulos , Volkan Cevher , Grigorios G. Chrysos

As large language models (LLMs) are becoming more capable and widespread, the study of their failure cases is becoming increasingly important. Recent advances in standardizing, measuring, and scaling test-time compute suggest new…

Machine Learning · Computer Science 2025-06-26 Mahdi Sabbaghi , Paul Kassianik , George Pappas , Yaron Singer , Amin Karbasi , Hamed Hassani

Large language models achieve strong performance in language generation and knowledge-intensive tasks, yet remain limited in settings requiring causal reasoning, persistent state tracking, and long-horizon planning. We argue that these…

Artificial Intelligence · Computer Science 2026-05-26 Feisal Alaswad , Batoul Aljaddouh , Maher Alrahhal , Poovammal E , Talal Bonny

Large Language Models (LLMs) deployed in production environments face a fundamental safety-utility trade-off either a strict filtering mechanisms prevent harmful outputs but often block benign queries or a relaxed controls risk unsafe…

Artificial Intelligence · Computer Science 2026-02-18 Ankit Sharma , Nachiket Tapas , Jyotiprakash Patra

Effective incident response (IR) is critical for mitigating cyber threats, yet security teams are overwhelmed by alert fatigue, high false-positive rates, and the vast volume of unstructured Cyber Threat Intelligence (CTI) documents. While…

Cryptography and Security · Computer Science 2025-08-15 Amine Tellache , Abdelaziz Amara Korba , Amdjed Mokhtari , Horea Moldovan , Yacine Ghamri-Doudane

Preference-based post-training aligns LLMs with human intent, yet safety behavior often remains brittle. A model may refuse a harmful request in a standard prompt but comply when the same intent is wrapped in adversarial wording. We suggest…

Computation and Language · Computer Science 2026-05-21 Yixu Wang , Yang Yao , Xin Wang , Yifeng Gao , Yan Teng , Xingjun Ma , Yingchun Wang

The integration of large language models (LLMs) into enterprise systems has introduced a new class of covert security vulnerabilities, particularly within logic execution layers and persistent memory contexts. This paper introduces…

Cryptography and Security · Computer Science 2025-08-08 Hammad Atta , Ken Huang , Manish Bhatt , Kamal Ahmed , Muhammad Aziz Ul Haq , Yasir Mehmood

While Large Language Models (LLMs) demonstrate exceptional performance in surface-level text generation, their nature in handling complex multi-step reasoning tasks often remains one of ``statistical fitting'' rather than systematic logical…

Machine Learning · Computer Science 2026-01-27 Lianlei Shan , Han Chen , Yixuan Wang , Zhenjie Liu , Wei Li

Modern large language model (LLM) developers typically conduct a safety alignment to prevent an LLM from generating unethical or harmful content. Recent studies have discovered that the safety alignment of LLMs can be bypassed by…

Cryptography and Security · Computer Science 2024-06-14 Xuan Chen , Yuzhou Nie , Lu Yan , Yunshu Mao , Wenbo Guo , Xiangyu Zhang

Large language models (LLMs) excel in diverse applications but face dual challenges: generating harmful content under jailbreak attacks and over-refusal of benign queries due to rigid safety mechanisms. These issues are further complicated…

Artificial Intelligence · Computer Science 2025-11-04 Yifan Xia , Guorui Chen , Wenqian Yu , Zhijiang Li , Philip Torr , Jindong Gu

The Dynamic Flexible Job Shop Scheduling Problem (DFJSP) necessitates a trade-off between instant reaction to stochastic disturbances and global optimization of production goals. Conventional priority rules are insufficiently flexible to…

Artificial Intelligence · Computer Science 2026-05-29 Shijie Cao , Yuan Yuan , Jing Liu

When answering user queries, LLMs often retrieve knowledge from external sources stored in retrieval-augmented generation (RAG) databases. These are often populated from unvetted sources, e.g. the open web, and can contain maliciously…

Cryptography and Security · Computer Science 2026-03-27 Hao Wu , Prateek Saxena

Safety alignment approaches in large language models (LLMs) often lead to the over-refusal of benign queries, significantly diminishing their utility in sensitive scenarios. To address this challenge, we introduce FalseReject, a…

Computation and Language · Computer Science 2025-07-16 Zhehao Zhang , Weijie Xu , Fanyou Wu , Chandan K. Reddy

Large language models (LLMs) process entire input contexts indiscriminately, which is inefficient when the information required to answer a query is localized within the context. We present dynamic context cutoff, a novel method enabling…

Computation and Language · Computer Science 2026-02-10 Roy Xie , Junlin Wang , Paul Rosu , Chunyuan Deng , Bolun Sun , Zihao Lin , Bhuwan Dhingra

Large language models (LLMs) are shown to be vulnerable to jailbreaking attacks where adversarial prompts are designed to elicit harmful responses. While existing defenses effectively mitigate single-turn attacks by detecting and filtering…

Computation and Language · Computer Science 2026-02-17 Hanjiang Hu , Alexander Robey , Changliu Liu

AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions. This position paper discusses our…

Cryptography and Security · Computer Science 2026-04-01 Chong Xiang , Drew Zagieboylo , Shaona Ghosh , Sanjay Kariyappa , Kai Greshake , Hanshen Xiao , Chaowei Xiao , G. Edward Suh

Prompt injection is the most critical vulnerability in deployed AI agents. Despite recent progress, we show that the prevailing defense paradigm (data-instruction separation) both fails to detect attacks that operate through contextual…

Cryptography and Security · Computer Science 2026-05-19 Sahar Abdelnabi , Eugene Bagdasarian

While Multimodal Large Language Models (MLLMs) show remarkable capabilities, their safety alignments are susceptible to jailbreak attacks. Existing attack methods typically focus on text-image interplay, treating the visual modality as a…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Yuan Xiong , Ziqi Miao , Lijun Li , Chen Qian , Jie Li , Jing Shao