Practical Defences Against Model Inversion Attacks for Split Neural Networks
We describe a threat model under which a split network-based federated learning system is susceptible to a model inversion attack by a malicious computational server. We demonstrate that the attack can be successfully performed with limited knowledge of the data distribution by the attacker. We propose a simple additive noise method to defend against model inversion, finding that the method can significantly reduce attack efficacy at an acceptable accuracy trade-off on MNIST. Furthermore, we show that NoPeekNN, an existing defensive method, protects different information from exposure, suggesting that a combined defence is necessary to fully protect private user data.
Code (1)
Tasks
Federated LearningSimilar Papers 제목 키워드 기반
Adversarial Prompt Evaluation: Systematic Benchmarking of Guardrails Against Prompt Input Attacks on LLMs
As large language models (LLMs) become integrated into everyday applications, ensuring their robustness and security is increasingly critical. In particular, LLMs can be manipulated into unsafe behaviour by prompts known…
BenchmarkingAdversarial purification for no-reference image-quality metrics: applicability study and new methods
Recently, the area of adversarial attacks on image quality metrics has begun to be explored, whereas the area of defences remains under-researched. In this study, we aim to cover that case and check the transferability o…
Adversarial PurificationDenoisingSoK: Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning
Multi-Agent Reinforcement Learning (MARL) is vulnerable to Adversarial Machine Learning (AML) attacks and needs adequate defences before it can be used in real world applications. We have conducted a survey into the use …
Deep Reinforcement LearningMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning+1Preventing Adversarial AI Attacks Against Autonomous Situational Awareness: A Maritime Case Study
Adversarial artificial intelligence (AI) attacks pose a significant threat to autonomous transportation, such as maritime vessels, that rely on AI components. Malicious actors can exploit these systems to deceive and man…
Fundamental Limitations in Defending LLM Finetuning APIs
LLM developers have imposed technical interventions to prevent fine-tuning misuse attacks, attacks where adversaries evade safeguards by fine-tuning the model using a public API. Previous work has established several suc…
Multiple-choice