RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction

Jailbreak attacks circumvent LLMs' built-in safeguards by concealing harmful queries within jailbreak prompts. While existing defenses primarily focus on mitigating the effects of jailbreak prompts, they often prove inadequate as jailbreak prompts can take arbitrary, adaptive forms. This paper presents RobustKV, a novel defense that adopts a fundamentally different approach by selectively removing critical tokens of harmful queries from key-value (KV) caches. Intuitively, for a jailbreak prompt to be effective, its tokens must achieve sufficient `importance' (as measured by attention scores), which inevitably lowers the importance of tokens in the concealed harmful query. Thus, by strategically evicting the KVs of the lowest-ranked tokens, RobustKV diminishes the presence of the harmful query in the KV cache, thus preventing the LLM from generating malicious responses. Extensive evaluation using benchmark datasets and models demonstrates that RobustKV effectively counters state-of-the-art jailbreak attacks while maintaining the LLM's general performance on benign queries. Moreover, RobustKV creates an intriguing evasiveness dilemma for adversaries, forcing them to balance between evading RobustKV and bypassing the LLM's built-in safeguards. This trade-off contributes to RobustKV's robustness against adaptive attacks. (warning: this paper contains potentially harmful content generated by LLMs.)

Buckle Up: Robustifying LLMs at Every Customization Stage via Data Curation

Large language models (LLMs) are extensively adapted for downstream applications through a process known as "customization," with fine-tuning being a common method for integrating domain-specific expertise. However, recent studies have revealed a vulnerability that tuning LLMs with malicious samples can compromise their robustness and amplify harmful content, an attack known as "jailbreaking." To mitigate such attack, we propose an effective defensive framework utilizing data curation to revise commonsense texts and enhance their safety implication from the perspective of LLMs. The curated texts can mitigate jailbreaking attacks at every stage of the customization process: before customization to immunize LLMs against future jailbreak attempts, during customization to neutralize jailbreaking risks, or after customization to restore the compromised models. Since the curated data strengthens LLMs through the standard fine-tuning workflow, we do not introduce additional modules during LLM inference, thereby preserving the original customization process. Experimental results demonstrate a substantial reduction in jailbreaking effects, with up to a 100% success in generating responsible responses. Notably, our method is effective even with commonsense texts, which are often more readily available than safety-relevant data. With the every-stage defensive framework and supporting experimental performance, this work represents a significant advancement in mitigating jailbreaking risks and ensuring the secure customization of LLMs.

Robustifying Safety-Aligned Large Language Models through Clean Data Curation

Large language models (LLMs) are vulnerable when trained on datasets containing harmful content, which leads to potential jailbreaking attacks in two scenarios: the integration of harmful texts within crowdsourced data used for pre-training and direct tampering with LLMs through fine-tuning. In both scenarios, adversaries can compromise the safety alignment of LLMs, exacerbating malfunctions. Motivated by the need to mitigate these adversarial influences, our research aims to enhance safety alignment by either neutralizing the impact of malicious texts in pre-training datasets or increasing the difficulty of jailbreaking during downstream fine-tuning. In this paper, we propose a data curation framework designed to counter adversarial impacts in both scenarios. Our method operates under the assumption that we have no prior knowledge of attack details, focusing solely on curating clean texts. We introduce an iterative process aimed at revising texts to reduce their perplexity as perceived by LLMs, while simultaneously preserving their text quality. By pre-training or fine-tuning LLMs with curated clean texts, we observe a notable improvement in LLM robustness regarding safety alignment against harmful queries. For instance, when pre-training LLMs using a crowdsourced dataset containing 5\% harmful instances, adding an equivalent amount of curated texts significantly mitigates the likelihood of providing harmful responses in LLMs and reduces the attack success rate by 71\%. Our study represents a significant step towards mitigating the risks associated with training-based jailbreaking and fortifying the secure utilization of LLMs.

Model Extraction Attacks Revisited

Model extraction (ME) attacks represent one major threat to Machine-Learning-as-a-Service (MLaaS) platforms by ``stealing'' the functionality of confidential machine-learning models through querying black-box APIs. Over seven years have passed since ME attacks were first conceptualized in the seminal work. During this period, substantial advances have been made in both ME attacks and MLaaS platforms, raising the intriguing question: How has the vulnerability of MLaaS platforms to ME attacks been evolving? In this work, we conduct an in-depth study to answer this critical question. Specifically, we characterize the vulnerability of current, mainstream MLaaS platforms to ME attacks from multiple perspectives including attack strategies, learning techniques, surrogate-model design, and benchmark tasks. Many of our findings challenge previously reported results, suggesting emerging patterns of ME vulnerability. Further, by analyzing the vulnerability of the same MLaaS platforms using historical datasets from the past four years, we retrospectively characterize the evolution of ME vulnerability over time, leading to a set of interesting findings. Finally, we make suggestions about improving the current practice of MLaaS in terms of attack robustness. Our study sheds light on the current state of ME vulnerability in the wild and points to several promising directions for future research.

OmniLytics: A Blockchain-based Secure Data Market for Decentralized Machine Learning

We propose OmniLytics, a blockchain-based secure data trading marketplace for machine learning applications. Utilizing OmniLytics, many distributed data owners can contribute their private data to collectively train a ML model requested by some model owners, and get compensated for data contribution. OmniLytics enables such model training while simultaneously providing 1) model security against curious data owners; 2) data security against curious model and data owners; 3) resilience to malicious data owners who provide faulty results to poison model training; and 4) resilience to malicious model owner who intents to evade the payment. OmniLytics is implemented as a smart contract on the Ethereum blockchain to guarantee the atomicity of payment. In OmniLytics, a model owner publishes encrypted initial model on the contract, over which the participating data owners compute gradients using their private data, and securely aggregate the gradients through the contract. Finally, the contract reimburses the data owners, and the model owner decrypts the aggregated model update. We implement a working prototype of OmniLytics on Ethereum, and perform extensive experiments to measure its gas cost and execution time under various parameter combinations, demonstrating its high computation and cost efficiency and strong practicality.