When large language models are trained on private data, it can be a significant privacy risk for them to memorize and regurgitate sensitive information. In this work, we propose a new practical data extraction attack that we call "neural phishing". This attack enables an adversary to target and extract sensitive or personally identifiable information (PII), e.g., credit card numbers, from a model trained on user data with upwards of 10% attack success rates, at times, as high as 50%. Our attack assumes only that an adversary can insert as few as 10s of benign-appearing sentences into the training dataset using only vague priors on the structure of the user data.
Large language models (LLMs) show inherent brittleness in their safety mechanisms, as evidenced by their susceptibility to jailbreaking and even non-malicious fine-tuning. This study explores this brittleness of safety alignment by leveraging pruning and low-rank modifications. We develop methods to identify critical regions that are vital for safety guardrails, and that are disentangled from utility-relevant regions at both the neuron and rank levels. Surprisingly, the isolated regions we find are sparse, comprising about $3\%$ at the parameter level and $2.5\%$ at the rank level. Removing these regions compromises safety without significantly impacting utility, corroborating the inherent brittleness of the model's safety mechanisms. Moreover, we show that LLMs remain vulnerable to low-cost fine-tuning attacks even when modifications to the safety-critical regions are restricted. These findings underscore the urgent need for more robust safety strategies in LLMs.
This work aims to address an open problem in data valuation literature concerning the efficient computation of Data Shapley for weighted $K$ nearest neighbor algorithm (WKNN-Shapley). By considering the accuracy of hard-label KNN with discretized weights as the utility function, we reframe the computation of WKNN-Shapley into a counting problem and introduce a quadratic-time algorithm, presenting a notable improvement from $O(N^K)$, the best result from existing literature. We develop a deterministic approximation algorithm that further improves computational efficiency while maintaining the key fairness properties of the Shapley value. Through extensive experiments, we demonstrate WKNN-Shapley's computational efficiency and its superior performance in discerning data quality compared to its unweighted counterpart.
Fine-tuning large pretrained models on private datasets may run the risk of violating privacy. Differential privacy is a framework for mitigating privacy risks by enforcing algorithmic stability. DP-SGD enables training models with private data in a privacy-preserving manner, but raises new obstacles in the form of performance loss and significant engineering challenges. We introduce DP-ZO, a new method for fine-tuning large language models that preserves the privacy of training data by privatizing zeroth-order optimization. A key insight into the design of our method is that the direction of the gradient in SPSA, the zeroth-order algorithm we use, is always random and the only information that depends on private data is the step size, i.e., a scalar. Therefore, we only need to privatize the scalar step size, which is memory-efficient. DP-ZO, which can be instantiated with either Laplace or Gaussian noise, provides a strong privacy-utility trade-off across different tasks, and model sizes, under conservative privacy budgets. One noteworthy result is that DP-ZO exhibits just $1.86\%$ performance degradation due to privacy at $(1,10^{-5})$-DP when fine-tuning OPT-66B on 1000 training samples from SQuAD.
State-of-the-art defenses against adversarial patch attacks can now achieve strong certifiable robustness with a marginal drop in model utility. However, this impressive performance typically comes at the cost of 10-100x more inference-time computation compared to undefended models -- the research community has witnessed an intense three-way trade-off between certifiable robustness, model utility, and computation efficiency. In this paper, we propose a defense framework named PatchCURE to approach this trade-off problem. PatchCURE provides sufficient "knobs" for tuning defense performance and allows us to build a family of defenses: the most robust PatchCURE instance can match the performance of any existing state-of-the-art defense (without efficiency considerations); the most efficient PatchCURE instance has similar inference efficiency as undefended models. Notably, PatchCURE achieves state-of-the-art robustness and utility performance across all different efficiency levels, e.g., 16-23% absolute clean accuracy and certified robust accuracy advantages over prior defenses when requiring computation efficiency to be close to undefended models. The family of PatchCURE defenses enables us to flexibly choose appropriate defenses to satisfy given computation and/or utility constraints in practice.
Optimizing large language models (LLMs) for downstream use cases often involves the customization of pre-trained LLMs through further fine-tuning. Meta's open release of Llama models and OpenAI's APIs for fine-tuning GPT-3.5 Turbo on custom datasets also encourage this practice. But, what are the safety costs associated with such custom fine-tuning? We note that while existing safety alignment infrastructures can restrict harmful behaviors of LLMs at inference time, they do not cover safety risks when fine-tuning privileges are extended to end-users. Our red teaming studies find that the safety alignment of LLMs can be compromised by fine-tuning with only a few adversarially designed training examples. For instance, we jailbreak GPT-3.5 Turbo's safety guardrails by fine-tuning it on only 10 such examples at a cost of less than $0.20 via OpenAI's APIs, making the model responsive to nearly any harmful instructions. Disconcertingly, our research also reveals that, even without malicious intent, simply fine-tuning with benign and commonly used datasets can also inadvertently degrade the safety alignment of LLMs, though to a lesser extent. These findings suggest that fine-tuning aligned LLMs introduces new safety risks that current safety infrastructures fall short of addressing -- even if a model's initial safety alignment is impeccable, it is not necessarily to be maintained after custom fine-tuning. We outline and critically analyze potential mitigations and advocate for further research efforts toward reinforcing safety protocols for the custom fine-tuning of aligned LLMs.
Data valuation, a critical aspect of data-centric ML research, aims to quantify the usefulness of individual data sources in training machine learning (ML) models. However, data valuation faces significant yet frequently overlooked privacy challenges despite its importance. This paper studies these challenges with a focus on KNN-Shapley, one of the most practical data valuation methods nowadays. We first emphasize the inherent privacy risks of KNN-Shapley, and demonstrate the significant technical difficulties in adapting KNN-Shapley to accommodate differential privacy (DP). To overcome these challenges, we introduce TKNN-Shapley, a refined variant of KNN-Shapley that is privacy-friendly, allowing for straightforward modifications to incorporate DP guarantee (DP-TKNN-Shapley). We show that DP-TKNN-Shapley has several advantages and offers a superior privacy-utility tradeoff compared to naively privatized KNN-Shapley in discerning data quality. Moreover, even non-private TKNN-Shapley achieves comparable performance as KNN-Shapley. Overall, our findings suggest that TKNN-Shapley is a promising alternative to KNN-Shapley, particularly for real-world applications involving sensitive data.
We present a novel defense, against backdoor attacks on Deep Neural Networks (DNNs), wherein adversaries covertly implant malicious behaviors (backdoors) into DNNs. Our defense falls within the category of post-development defenses that operate independently of how the model was generated. The proposed defense is built upon a novel reverse engineering approach that can directly extract backdoor functionality of a given backdoored model to a backdoor expert model. The approach is straightforward -- finetuning the backdoored model over a small set of intentionally mislabeled clean samples, such that it unlearns the normal functionality while still preserving the backdoor functionality, and thus resulting in a model (dubbed a backdoor expert model) that can only recognize backdoor inputs. Based on the extracted backdoor expert model, we show the feasibility of devising highly accurate backdoor input detectors that filter out the backdoor inputs during model inference. Further augmented by an ensemble strategy with a finetuned auxiliary model, our defense, BaDExpert (Backdoor Input Detection with Backdoor Expert), effectively mitigates 16 SOTA backdoor attacks while minimally impacting clean utility. The effectiveness of BaDExpert has been verified on multiple datasets (CIFAR10, GTSRB and ImageNet) across various model architectures (ResNet, VGG, MobileNetV2 and Vision Transformer).
Food classification is an important task in health care. In this work, we propose a multimodal classification framework that uses the modified version of EfficientNet with the Mish activation function for image classification, and the traditional BERT transformer-based network is used for text classification. The proposed network and the other state-of-the-art methods are evaluated on a large open-source dataset, UPMC Food-101. The experimental results show that the proposed network outperforms the other methods, a significant difference of 11.57% and 6.34% in accuracy is observed for image and text classification, respectively, when compared with the second-best performing method. We also compared the performance in terms of accuracy, precision, and recall for text classification using both machine learning and deep learning-based models. The comparative analysis from the prediction results of both images and text demonstrated the efficiency and robustness of the proposed approach.
Recently, there has been a surge of interest in introducing vision into Large Language Models (LLMs). The proliferation of large Visual Language Models (VLMs), such as Flamingo, BLIP-2, and GPT-4, signifies an exciting convergence of advancements in both visual and language foundation models. Yet, the risks associated with this integrative approach are largely unexamined. In this paper, we shed light on the security and safety implications of this trend. First, we underscore that the continuous and high-dimensional nature of the additional visual input space intrinsically makes it a fertile ground for adversarial attacks. This unavoidably expands the attack surfaces of LLMs. Second, we highlight that the broad functionality of LLMs also presents visual attackers with a wider array of achievable adversarial objectives, extending the implications of security failures beyond mere misclassification. To elucidate these risks, we study adversarial examples in the visual input space of a VLM. Specifically, against MiniGPT-4, which incorporates safety mechanisms that can refuse harmful instructions, we present visual adversarial examples that can circumvent the safety mechanisms and provoke harmful behaviors of the model. Remarkably, we discover that adversarial examples, even if optimized on a narrow, manually curated derogatory corpus against specific social groups, can universally jailbreak the model's safety mechanisms. A single such adversarial example can generally undermine MiniGPT-4's safety, enabling it to heed a wide range of harmful instructions and produce harmful content far beyond simply imitating the derogatory corpus used in optimization. Unveiling these risks, we accentuate the urgent need for comprehensive risk assessments, robust defense strategies, and the implementation of responsible practices for the secure and safe utilization of VLMs.