English
Related papers

Related papers: Stateful Agent Backdoor

200 papers

With the success of deep learning algorithms in various domains, studying adversarial attacks to secure deep models in real world applications has become an important research topic. Backdoor attacks are a form of adversarial attacks on…

Computer Vision and Pattern Recognition · Computer Science 2019-12-24 Aniruddha Saha , Akshayvarun Subramanya , Hamed Pirsiavash

Large language model (LLM) agents increasingly operate in settings where a single context window is far too small to capture what has happened, what was learned, and what should not be repeated. Memory -- the ability to persist, organize,…

Artificial Intelligence · Computer Science 2026-03-10 Pengfei Du

Federated learning enables thousands of participants to construct a deep learning model without sharing their private training data with each other. For example, multiple smartphones can jointly train a next-word predictor for keyboards…

Cryptography and Security · Computer Science 2019-08-07 Eugene Bagdasaryan , Andreas Veit , Yiqing Hua , Deborah Estrin , Vitaly Shmatikov

Reinforcement Learning (RL) agents often struggle to generalize knowledge to new tasks, even those structurally similar to ones they have mastered. Although recent approaches have attempted to mitigate this issue via zero-shot transfer,…

Artificial Intelligence · Computer Science 2026-04-13 Ajsal Shereef Palattuparambil , Thommen George Karimpanal , Santu Rana

This paper presents SANDMAN, an architecture for cyber deception that leverages Language Agents to emulate convincing human simulacra. Our 'Deceptive Agents' serve as advanced cyber decoys, designed for high-fidelity engagement with…

Artificial Intelligence · Computer Science 2025-03-26 Lewis Newsham , Ryan Hyland , Daniel Prince

Backdoor attacks are commonly executed by contaminating training data, such that a trigger can activate predetermined harmful effects during the test phase. In this work, we present AnyDoor, a test-time backdoor attack against multimodal…

Computation and Language · Computer Science 2024-02-14 Dong Lu , Tianyu Pang , Chao Du , Qian Liu , Xianjun Yang , Min Lin

A backdoor attack allows a malicious user to manipulate the environment or corrupt the training data, thus inserting a backdoor into the trained agent. Such attacks compromise the RL system's reliability, leading to potentially catastrophic…

Machine Learning · Computer Science 2023-04-11 Hao Chen , Chen Gong , Yizhe Wang , Xinwen Hou

Due to their decentralized nature, federated learning (FL) systems have an inherent vulnerability during their training to adversarial backdoor attacks. In this type of attack, the goal of the attacker is to use poisoned updates to implant…

Cryptography and Security · Computer Science 2022-06-22 Zhengming Zhang , Ashwinee Panda , Linyue Song , Yaoqing Yang , Michael W. Mahoney , Joseph E. Gonzalez , Kannan Ramchandran , Prateek Mittal

LLM agents increasingly rely on persistent state, including transcripts, summaries, retrieved context, and memory buffers, to support long-horizon interaction. This makes safety depend not only on individual model outputs, but also on what…

Artificial Intelligence · Computer Science 2026-05-19 Yian Wang , Agam Goyal , Yuen Chen , Hari Sundaram

Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as jailbreak attacks that circumvent built-in safety mechanisms.…

Artificial Intelligence · Computer Science 2025-10-01 Qinjian Zhao , Jiaqi Wang , Zhiqiang Gao , Zhihao Dou , Belal Abuhaija , Kaizhu Huang

Recent studies have shown that Large Language Models (LLMs) are vulnerable to data poisoning attacks, where malicious training examples embed hidden behaviours triggered by specific input patterns. However, most existing works assume a…

Computation and Language · Computer Science 2025-10-10 Sanhanat Sivapiromrat , Caiqi Zhang , Marco Basaldella , Nigel Collier

In this brief, we show that sequentially learning new information presented to a continual (incremental) learning model introduces new security risks: an intelligent adversary can introduce small amount of misinformation to the model during…

Machine Learning · Computer Science 2022-02-10 Muhammad Umer , Robi Polikar

Embodied Large Language Models (LLMs) enable AI agents to interact with the physical world through natural language instructions and actions. However, beyond the language-level risks inherent to LLMs themselves, embodied LLMs with…

Robotics · Computer Science 2026-03-03 Xinyu Huang , Qiang Yang , Leming Shen , Zijing Ma , Yuanqing Zheng

Pre-trained language models (PLMs) have been widely used to underpin various downstream tasks. However, the adversarial attack task has found that PLMs are vulnerable to small perturbations. Mainstream methods adopt a detached two-stage…

Computation and Language · Computer Science 2023-05-30 Xuanjie Fang , Sijie Cheng , Yang Liu , Wei Wang

Large language models (LLMs) have made remarkable strides in complex reasoning tasks, but their safety and robustness in reasoning processes remain underexplored. Existing attacks on LLM reasoning are constrained by specific settings or…

Artificial Intelligence · Computer Science 2025-06-17 Jingyu Peng , Maolin Wang , Xiangyu Zhao , Kai Zhang , Wanyu Wang , Pengyue Jia , Qidong Liu , Ruocheng Guo , Qi Liu

Connecting large language models (LLMs) to defensive enforcement requires more than asking a model whether an attack is happening. A defender must decide which model outputs may change the system state, which outputs must be rejected, and…

Cryptography and Security · Computer Science 2026-05-22 Sidnei Barbieri , Ágney Lopes Roth Ferraz , Lourenço Alves Pereira Júnior

Early research into data poisoning attacks against Large Language Models (LLMs) demonstrated the ease with which backdoors could be injected. More recent LLMs add step-by-step reasoning, expanding the attack surface to include the…

Cryptography and Security · Computer Science 2025-09-09 Hanna Foerster , Ilia Shumailov , Yiren Zhao , Harsh Chaudhari , Jamie Hayes , Robert Mullins , Yarin Gal

Backdoors are hidden behaviors that are only triggered once an AI system has been deployed. Bad actors looking to create successful backdoors must design them to avoid activation during training and evaluation. Since data used in these…

Cryptography and Security · Computer Science 2024-12-25 Sara Price , Arjun Panickssery , Sam Bowman , Asa Cooper Stickland

Effective navigation intelligence relies on long-term memory to support both immediate generalization and sustained adaptation. However, existing approaches face a dilemma: modular systems rely on explicit mapping but lack flexibility,…

Machine Learning · Computer Science 2026-03-26 Zhiyuan Chen , Yuxuan Zhong , Fan Wang , Bo Yu , Pengtao Shao , Shaoshan Liu , Ning Ding

Code models are increasingly adopted in software development but remain vulnerable to backdoor attacks via poisoned training data. Existing backdoor attacks on code models face a fundamental trade-off between transferability and…

Cryptography and Security · Computer Science 2026-02-13 Shuyu Chang , Haiping Huang , Yanjun Zhang , Yujin Huang , Fu Xiao , Leo Yu Zhang
‹ Prev 1 8 9 10 Next ›