Turning Federated Learning Systems Into Covert Channels
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningModel PoisoningSimilar Papers 제목 키워드 기반
Achieving Positive Covert Capacity over MIMO AWGN Channels
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
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 LearningTool Use Enables Undetectable Steganography in Multi-Agent LLM Systems
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
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
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