paper-with-me

홈 › Papers

Turning Federated Learning Systems Into Covert Channels

2021-04-21 · Gabriele Costa, Fabio Pinelli, Simone Soderi, Gabriele Tolomei

Federated learning (FL) goes beyond traditional, centralized machine learning by distributing model training among a large collection of edge clients. These clients cooperatively train a global, e.g., cloud-hosted, model without disclosing their local, private training data. The global model is then shared among all the participants which use it for local predictions. In this paper, we put forward a novel attacker model aiming at turning FL systems into covert channels to implement a stealth communication infrastructure. The main intuition is that, during federated training, a malicious sender can poison the global model by submitting purposely crafted examples. Although the effect of the model poisoning is negligible to other participants, and does not alter the overall model performance, it can be observed by a malicious receiver and used to transmit a single bit.

📄 PDF Abstract BibTeX arXiv:2104.10561

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningModel Poisoning

Similar Papers 제목 키워드 기반

Achieving Positive Covert Capacity over MIMO AWGN Channels

2019-10-30

We consider covert communication, i.e., hiding the presence of communication from an adversary for multiple-input multiple-output (MIMO) additive white Gaussian noise (AWGN) channels. We characterize the maximum covert c…

Covert Communication Based on the Poisoning Attack in Federated Learning

2023-06-02 · Junchuan Liang, Rong Wang

Covert communication has become an important area of research in computer security. It involves hiding specific information on a carrier for message transmission and is often used to transmit private data, military secre…

Computer SecurityFederated Learning

Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems

2026-06-25 · Jimmy Laurence Rippin, Simon C. Marshall, David Demitri Africa, Christian Schroeder de Witt arxiv

Increasingly autonomous agentic AI systems pose novel multi-agent risks, such as secret collusion via covert communication channels. The natural defence to these collusion attempts is to monitor plain-text communication,…

Will the User Ever Know? Covert Indirect Prompt Injection on Tool-Using LLM Agents

2026-08-31 · Yunseok Lee, Yunji Kim, Woojin Lee arxiv

As LLM agents take real-world actions through tools, indirect prompt injection (IPI) has emerged as a serious threat. The standard metric, Attack Success Rate (ASR), counts whether an injection succeeds but ignores what …

FedAttack: Effective and Covert Poisoning Attack on Federated Recommendation via Hard Sampling

2022-02-10 · Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang 외

Federated learning (FL) is a feasible technique to learn personalized recommendation models from decentralized user data. Unfortunately, federated recommender systems are vulnerable to poisoning attacks by malicious clie…

Federated LearningRecommendation Systems