English
Related papers

Related papers: SafeHarbor: Hierarchical Memory-Augmented Guardrai…

200 papers

Recent advances in large language models (LLMs) have led to increasingly sophisticated safety protocols and features designed to prevent harmful, unethical, or unauthorized outputs. However, these guardrails remain susceptible to novel and…

Computation and Language · Computer Science 2025-07-08 Annika M Schoene , Cansu Canca

The recent breakthrough in large language models (LLMs) such as ChatGPT has revolutionized production processes at an unprecedented pace. Alongside this progress also comes mounting concerns about LLMs' susceptibility to jailbreaking…

Machine Learning · Computer Science 2024-05-24 Tianrong Zhang , Bochuan Cao , Yuanpu Cao , Lu Lin , Prasenjit Mitra , Jinghui Chen

We introduce a defense against adversarial attacks on LLMs utilizing self-evaluation. Our method requires no model fine-tuning, instead using pre-trained models to evaluate the inputs and outputs of a generator model, significantly reducing…

Machine Learning · Computer Science 2024-08-07 Hannah Brown , Leon Lin , Kenji Kawaguchi , Michael Shieh

Large language models (LLMs) and multimodal LLMs are typically safety-aligned before release to prevent harmful content generation. However, recent studies show that safety behaviors are concentrated in a small subset of parameters, making…

Machine Learning · Computer Science 2026-02-13 Zhaoxin Wang , Jiaming Liang , Fengbin Zhu , Weixiang Zhao , Junfeng Fang , Jiayi Ji , Handing Wang , Tat-Seng Chua

While server-side Large Language Models (LLMs) demonstrate proficiency in function calling and complex reasoning, deploying Small Language Models (SLMs) directly on devices brings opportunities to improve latency and privacy but also…

Computation and Language · Computer Science 2024-10-15 Yicheng Fu , Raviteja Anantha , Jianpeng Cheng

Recent advances in large language models (LLMs) have raised concerns about jailbreaking attacks, i.e., prompts that bypass safety mechanisms. This paper investigates the use of multi-agent LLM systems as a defence against such attacks. We…

Artificial Intelligence · Computer Science 2025-07-01 Maria Carolina Cornelia Wit , Jun Pang

Maintaining the safety of large language models (LLMs) is crucial as they are increasingly deployed in real-world applications. Existing safety guardrails typically rely on single-pass classification or, more recently, distilled reasoning.…

Artificial Intelligence · Computer Science 2026-05-29 Siddharth Sai , Xiaofei Wen , Muhao Chen

Multi-agent systems built on Large Language Models (LLMs) show exceptional promise for complex collaborative problem-solving, yet they face fundamental challenges stemming from context window limitations that impair memory consistency, role…

Artificial Intelligence · Computer Science 2026-01-13 Sizhe Yuen , Francisco Gomez Medina , Ting Su , Yali Du , Adam J. Sobey

While safe reinforcement learning (RL) holds great promise for many practical applications like robotics or autonomous cars, current approaches require specifying constraints in mathematical form. Such specifications demand domain…

Computation and Language · Computer Science 2021-08-05 Tsung-Yen Yang , Michael Hu , Yinlam Chow , Peter J. Ramadge , Karthik Narasimhan

With the extensive deployment of Large Language Models (LLMs), ensuring their safety has become increasingly critical. However, existing defense methods often struggle with two key issues: (i) inadequate defense capabilities, particularly…

Artificial Intelligence · Computer Science 2025-02-11 Weidi Luo , He Cao , Zijing Liu , Yu Wang , Aidan Wong , Bing Feng , Yuan Yao , Yu Li

LLM-powered agents face a persistent challenge: learning from their execution experiences to improve future performance. While agents can successfully complete many tasks, they often repeat inefficient patterns, fail to recover from similar…

Artificial Intelligence · Computer Science 2026-03-12 Gaodan Fang , Vatche Isahagian , K. R. Jayaram , Ritesh Kumar , Vinod Muthusamy , Punleuk Oum , Gegi Thomas

Building LLM-based agents has become increasingly important. Recent works on LLM-based agent self-evolution primarily record successful experiences as textual prompts or reflections, which cannot reliably guarantee efficient task…

Artificial Intelligence · Computer Science 2026-03-19 Zhang Zhang , Shuqi Lu , Hongjin Qian , Di He , Zheng Liu

Large Language Models (LLMs) have gained widespread popularity across diverse domains involving text generation, summarization, and various natural language processing tasks. Despite their inherent limitations, LLM-based designs have shown…

Cryptography and Security · Computer Science 2024-04-17 Maria Rigaki , Ondřej Lukáš , Carlos A. Catania , Sebastian Garcia

Large language models (LLMs), known for their capability in understanding and following instructions, are vulnerable to adversarial attacks. Researchers have found that current commercial LLMs either fail to be "harmless" by presenting…

Cryptography and Security · Computer Science 2023-10-05 Bocheng Chen , Advait Paliwal , Qiben Yan

Web agents powered by vision-language models (VLMs) enable autonomous interaction with web environments by perceiving and acting on both visual and textual webpage content to accomplish user-specified tasks. However, they are highly…

Cryptography and Security · Computer Science 2026-04-15 Yulin Chen , Tri Cao , Haoran Li , Yue Liu , Yibo Li , Yufei He , Le Minh Khoi , Yangqiu Song , Shuicheng Yan , Bryan Hooi

LLM-based role-playing has rapidly improved in fidelity, yet stronger adherence to persona constraints commonly increases vulnerability to jailbreak attacks, especially for risky or negative personas. Most prior work mitigates this issue…

Artificial Intelligence · Computer Science 2026-02-17 Mingyang Liao , Yichen Wan , shuchen wu , Chenxi Miao , Xin Shen , Weikang Li , Yang Li , Deguo Xia , Jizhou Huang

Despite the promise of autonomous agentic reasoning, existing workflow generation methods frequently produce fragile, unexecutable plans due to unconstrained LLM-driven construction. We introduce MermaidFlow, a framework that redefines the…

Machine Learning · Computer Science 2025-05-30 Chengqi Zheng , Jianda Chen , Yueming Lyu , Wen Zheng Terence Ng , Haopeng Zhang , Yew-Soon Ong , Ivor Tsang , Haiyan Yin

The rapid advancement of large language models (LLMs) has driven their adoption across diverse domains, yet their ability to generate harmful content poses significant safety challenges. While extensive research has focused on mitigating…

Artificial Intelligence · Computer Science 2025-08-29 Yuanzhe Shen , Zisu Huang , Zhengkang Guo , Yide Liu , Guanxu Chen , Ruicheng Yin , Xiaoqing Zheng , Xuanjing Huang

Despite efforts to align large language models (LLMs) with human intentions, widely-used LLMs such as GPT, Llama, and Claude are susceptible to jailbreaking attacks, wherein an adversary fools a targeted LLM into generating objectionable…

Machine Learning · Computer Science 2024-06-17 Alexander Robey , Eric Wong , Hamed Hassani , George J. Pappas

While Large Language Models (LLMs) have shown significant advancements in performance, various jailbreak attacks have posed growing safety and ethical risks. Malicious users often exploit adversarial context to deceive LLMs, prompting them…

Cryptography and Security · Computer Science 2025-08-15 Jinhwa Kim , Ian G. Harris