English
Related papers

Related papers: Safer Policy Compliance with Dynamic Epistemic Fal…

200 papers

Theorem proving serves as a major testbed for evaluating complex reasoning abilities in large language models (LLMs). However, traditional automated theorem proving (ATP) approaches rely heavily on formal proof systems that poorly align…

Computation and Language · Computer Science 2025-06-04 Ziyin Zhang , Jiahao Xu , Zhiwei He , Tian Liang , Qiuzhi Liu , Yansi Li , Linfeng Song , Zhenwen Liang , Zhuosheng Zhang , Rui Wang , Zhaopeng Tu , Haitao Mi , Dong Yu

This paper introduces a novel self-consciousness defense mechanism for Large Language Models (LLMs) to combat prompt injection attacks. Unlike traditional approaches that rely on external classifiers, our method leverages the LLM's inherent…

Artificial Intelligence · Computer Science 2025-10-03 Boshi Huang , Fabio Nonato de Paula

With the rise of advanced reasoning capabilities, large language models (LLMs) are receiving increasing attention. However, although reasoning improves LLMs' performance on downstream tasks, it also introduces new security risks, as…

Cryptography and Security · Computer Science 2025-10-10 Man Hu , Xinyi Wu , Zuofeng Suo , Jinbo Feng , Linghui Meng , Yanhao Jia , Anh Tuan Luu , Shuai Zhao

Knowledge-intensive multi-hop question answering (QA) tasks, which require integrating evidence from multiple sources to address complex queries, often necessitate multiple rounds of retrieval and iterative generation by large language…

Computation and Language · Computer Science 2025-06-24 Binquan Ji , Haibo Luo , Yifei Lu , Lei Hei , Jiaqi Wang , Tingjing Liao , Lingyu Wang , Shichao Wang , Feiliang Ren

Robust verbal confidence generated by large language models (LLMs) is crucial for the deployment of LLMs to help ensure transparency, trust, and safety in many applications, including those involving human-AI interactions. In this paper, we…

Computation and Language · Computer Science 2025-12-19 Stephen Obadinma , Xiaodan Zhu

Federated Learning (FL) in the Internet of Things (IoT) environments can enhance machine learning by utilising decentralised data, but at the same time, it might introduce significant privacy and security concerns due to the constrained…

Cryptography and Security · Computer Science 2024-07-26 Adel ElZemity , Budi Arief

Deep reinforcement learning algorithms can learn complex behavioral skills, but real-world application of these methods requires a large amount of experience to be collected by the agent. In practical settings, such as robotics, this…

Machine Learning · Computer Science 2017-11-21 Benjamin Eysenbach , Shixiang Gu , Julian Ibarz , Sergey Levine

Federated learning (FL) enhances privacy by keeping user data on local devices. However, emerging attacks have demonstrated that the updates shared by users during training can reveal significant information about their data. This has…

Large Language Models (LLMs) have gained significant attention in on-device applications due to their remarkable performance across real-world tasks. However, on-device LLMs often suffer from suboptimal performance due to hardware…

Computation and Language · Computer Science 2025-03-03 Kai Zhang , Congchao Wang , Liqian Peng , Alec Go , Xiaozhong Liu

Large Language Models (LLMs) have shown great potential in reasoning tasks through test-time scaling methods like self-consistency with majority voting. However, this approach often leads to diminishing returns in accuracy and high…

Machine Learning · Computer Science 2025-08-22 Yichao Fu , Xuewei Wang , Yuandong Tian , Jiawei Zhao

Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current methods face a dual challenge: they fail to infer users' deep implicit preferences (including…

Artificial Intelligence · Computer Science 2026-04-29 Peiming Li , Zhiyuan Hu , Yang Tang , Shiyu Li , Xi Chen

Although Aligned Large Language Models (LLMs) are trained to refuse harmful requests, they remain vulnerable to jailbreak attacks. Unfortunately, existing methods often focus on surface-level patterns, overlooking the deeper attack…

Cryptography and Security · Computer Science 2025-05-29 Shiyu Xiang , Ansen Zhang , Yanfei Cao , Yang Fan , Ronghao Chen

Large Language Model (LLM) applications are vulnerable to prompt injection and context manipulation attacks that traditional security models cannot prevent. We introduce two novel primitives--authenticated prompts and authenticated…

Cryptography and Security · Computer Science 2026-02-12 Mohan Rajagopalan , Vinay Rao

In Federated Learning (FL), a group of workers participate to build a global model under the coordination of one node, the chief. Regarding the cybersecurity of FL, some attacks aim at injecting the fabricated local model updates into the…

Machine Learning · Computer Science 2021-11-30 Ranwa Al Mallah , Godwin Badu-Marfo , Bilal Farooq

Large Language Models (LLMs) are vulnerable to adversarial attacks that bypass safety guidelines and generate harmful content. Mitigating these vulnerabilities requires defense mechanisms that are both robust and computationally efficient.…

Machine Learning · Computer Science 2025-11-18 Gil Goren , Shahar Katz , Lior Wolf

With the rapid rise of personalized AI, customized large language models (LLMs) equipped with Chain of Thought (COT) reasoning now power millions of AI agents. However, their complex reasoning processes introduce new and largely unexplored…

Cryptography and Security · Computer Science 2025-11-25 Zhen Guo , Shanghao Shi , Shamim Yazdani , Ning Zhang , Reza Tourani

The rapid advancement of large language models (LLMs) presents new security challenges, particularly in detecting machine-generated text used for misinformation, impersonation, and content forgery. Most existing detection approaches…

Computation and Language · Computer Science 2026-04-30 Siyuan Li , Aodu Wulianghai , Guangyan Li , Xi Lin , Qinghua Mao , Yuliang Chen , Jun Wu , Jianhua Li

Vulnerability of Frontier language models to misuse and jailbreaks has prompted the development of safety measures like filters and alignment training in an effort to ensure safety through robustness to adversarially crafted prompts. We…

Cryptography and Security · Computer Science 2024-10-31 David Glukhov , Ziwen Han , Ilia Shumailov , Vardan Papyan , Nicolas Papernot

Large language models (LLMs) are increasingly deployed in security-sensitive applications, where they must follow system- or developer-specified instructions that define the intended task behavior, while completing benign user requests.…

Cryptography and Security · Computer Science 2026-01-13 Shawn Li , Chenxiao Yu , Zhiyu Ni , Hao Li , Charith Peris , Chaowei Xiao , Yue Zhao

Logic locking (LL) has gained attention as a promising intellectual property protection measure for integrated circuits. However, recent attacks, facilitated by machine learning (ML), have shown the potential to predict the correct key in…

Cryptography and Security · Computer Science 2024-03-05 Yinghua Hu , Kaixin Yang , Subhajit Dutta Chowdhury , Pierluigi Nuzzo