PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning

• URL: http://arxiv.org/abs/2411.19335v2
• Date: Thu, 19 Dec 2024 14:30:23 GMT
• Title: PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning
• Authors: Shenghui Li, Edith C. -H. Ngai, Fanghua Ye, Thiemo Voigt,
• Abstract summary: This paper introduces a novel security threat to FedPEFT, termed PEFT-as-an-Attack (PaaA) Our evaluation of PaaA reveals that with less than 1% of the model's parameters set as trainable, and a small subset of clients acting maliciously, the attack achieves an approximate 80% attack success rate using representative PEFT methods such as LoRA. Our results underscore the urgent need for more effective defense mechanisms that simultaneously ensure security and maintain the performance of the FedPEFT paradigm.
• Score: 8.61459170031022
• License:
• Abstract: Federated Parameter-Efficient Fine-Tuning (FedPEFT) has emerged as a promising paradigm for privacy-preserving and efficient adaptation of Pre-trained Language Models (PLMs) in Federated Learning (FL) settings. It preserves data privacy by keeping the data decentralized and training the model on local devices, ensuring that raw data never leaves the user's device. Moreover, the integration of PEFT methods such as LoRA significantly reduces the number of trainable parameters compared to fine-tuning the entire model, thereby minimizing communication costs and computational overhead. Despite its potential, the security implications of FedPEFT remain underexplored. This paper introduces a novel security threat to FedPEFT, termed PEFT-as-an-Attack (PaaA), which exposes how PEFT can be exploited as an attack vector to circumvent PLMs' safety alignment and generate harmful content in response to malicious prompts. Our evaluation of PaaA reveals that with less than 1% of the model's parameters set as trainable, and a small subset of clients acting maliciously, the attack achieves an approximate 80% attack success rate using representative PEFT methods such as LoRA. To mitigate this threat, we further investigate potential defense strategies, including Robust Aggregation Schemes (RASs) and Post-PEFT Safety Alignment (PPSA). However, our empirical analysis highlights the limitations of these defenses, i.e., even the most advanced RASs, such as DnC and ClippedClustering, struggle to defend against PaaA in scenarios with highly heterogeneous data distributions. Similarly, while PPSA can reduce attack success rates to below 10%, it severely degrades the model's accuracy on the target task. Our results underscore the urgent need for more effective defense mechanisms that simultaneously ensure security and maintain the performance of the FedPEFT paradigm.

Related papers

• Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning Paradigm [8.905741632785183]
  We introduce Obliviate, a PEFT-integrable backdoor defense. We develop two techniques aimed at amplifying benign neurons within PEFT layers and penalizing the influence of trigger tokens. Our method exhibits robust defense capabilities against both task-specific backdoors and adaptive attacks.
  arXiv  Detail & Related papers  (2024-09-21T12:20:18Z)
• Resilience in Online Federated Learning: Mitigating Model-Poisoning Attacks via Partial Sharing [6.957420925496431]
  Federated learning (FL) allows training machine learning models on distributed data without compromising privacy. FL is vulnerable to model-poisoning attacks where malicious clients tamper with their local models to manipulate the global model. In this work, we investigate the resilience of the partial-sharing online FL (PSO-Fed) algorithm against such attacks.
  arXiv  Detail & Related papers  (2024-03-19T19:15:38Z)
• Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment [56.2017039028998]
  Fine-tuning of Language-Model-as-a-Service (LM) introduces new threats, particularly against the Fine-tuning based Jailbreak Attack (FJAttack) We propose the Backdoor Enhanced Safety Alignment method inspired by an analogy with the concept of backdoor attacks. Our comprehensive experiments demonstrate that through the Backdoor Enhanced Safety Alignment with adding as few as 11 safety examples, the maliciously finetuned LLMs will achieve similar safety performance as the original aligned models without harming the benign performance.
  arXiv  Detail & Related papers  (2024-02-22T21:05:18Z)
• Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning [57.50274256088251]
  We show that parameter-efficient fine-tuning (PEFT) is more susceptible to weight-poisoning backdoor attacks. We develop a Poisoned Sample Identification Module (PSIM) leveraging PEFT, which identifies poisoned samples through confidence. We conduct experiments on text classification tasks, five fine-tuning strategies, and three weight-poisoning backdoor attack methods.
  arXiv  Detail & Related papers  (2024-02-19T14:22:54Z)
• FedRDF: A Robust and Dynamic Aggregation Function against Poisoning Attacks in Federated Learning [0.0]
  Federated Learning (FL) represents a promising approach to typical privacy concerns associated with centralized Machine Learning (ML) deployments. Despite its well-known advantages, FL is vulnerable to security attacks such as Byzantine behaviors and poisoning attacks. Our proposed approach was tested against various model poisoning attacks, demonstrating superior performance over state-of-the-art aggregation methods.
  arXiv  Detail & Related papers  (2024-02-15T16:42:04Z)
• PETA: Parameter-Efficient Trojan Attacks [10.327226660571121]
  We present PETA, a novel trojan attack that compromises the weights of PLMs. We demonstrate PETA's effectiveness in terms of both attack success rate and clean accuracy, even when the attacker does not have full knowledge of the victim user's training process.
  arXiv  Detail & Related papers  (2023-10-01T12:07:44Z)
• G$^2$uardFL: Safeguarding Federated Learning Against Backdoor Attacks through Attributed Client Graph Clustering [116.4277292854053]
  Federated Learning (FL) offers collaborative model training without data sharing. FL is vulnerable to backdoor attacks, where poisoned model weights lead to compromised system integrity. We present G$2$uardFL, a protective framework that reinterprets the identification of malicious clients as an attributed graph clustering problem.
  arXiv  Detail & Related papers  (2023-06-08T07:15:04Z)
• Avoid Adversarial Adaption in Federated Learning by Multi-Metric Investigations [55.2480439325792]
  Federated Learning (FL) facilitates decentralized machine learning model training, preserving data privacy, lowering communication costs, and boosting model performance through diversified data sources. FL faces vulnerabilities such as poisoning attacks, undermining model integrity with both untargeted performance degradation and targeted backdoor attacks. We define a new notion of strong adaptive adversaries, capable of adapting to multiple objectives simultaneously. MESAS is the first defense robust against strong adaptive adversaries, effective in real-world data scenarios, with an average overhead of just 24.37 seconds.
  arXiv  Detail & Related papers  (2023-06-06T11:44:42Z)
• FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning [66.56240101249803]
  We study how hardening benign clients can affect the global model (and the malicious clients) We propose a trigger reverse engineering based defense and show that our method can achieve improvement with guarantee robustness. Our results on eight competing SOTA defense methods show the empirical superiority of our method on both single-shot and continuous FL backdoor attacks.
  arXiv  Detail & Related papers  (2022-10-23T22:24:03Z)
• Federated Learning with Unreliable Clients: Performance Analysis and Mechanism Design [76.29738151117583]
  Federated Learning (FL) has become a promising tool for training effective machine learning models among distributed clients. However, low quality models could be uploaded to the aggregator server by unreliable clients, leading to a degradation or even a collapse of training. We model these unreliable behaviors of clients and propose a defensive mechanism to mitigate such a security risk.
  arXiv  Detail & Related papers  (2021-05-10T08:02:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.