Tian Dong

Tian Dong, Yan Meng, Shaofeng Li et al.

Large Language Models (LLMs) are increasingly integrated into daily routines, yet they raise significant privacy and safety concerns. Recent research proposes collaborative inference, which outsources the early-layer inference to ensure data locality, and introduces model safety auditing based on inner neuron patterns. Both techniques expose the LLM's Internal States (ISs), which are traditionally considered irreversible to inputs due to optimization challenges and the highly abstract representations in deep layers. In this work, we challenge this assumption by proposing four inversion attacks that significantly improve the semantic similarity and token matching rate of inverted inputs. Specifically, we first develop two white-box optimization-based attacks tailored for low-depth and high-depth ISs. These attacks avoid local minima convergence, a limitation observed in prior work, through a two-phase inversion process. Then, we extend our optimization attack under more practical black-box weight access by leveraging the transferability between the source and the derived LLMs. Additionally, we introduce a generation-based attack that treats inversion as a translation task, employing an inversion model to reconstruct inputs. Extensive evaluation of short and long prompts from medical consulting and coding assistance datasets and 6 LLMs validates the effectiveness of our inversion attacks. Notably, a 4,112-token long medical consulting prompt can be nearly perfectly inverted with 86.88 F1 token matching from the middle layer of Llama-3 model. Finally, we evaluate four practical defenses that we found cannot perfectly prevent ISs inversion and draw conclusions for future mitigation design.

Tian Dong, Han Qiu, Tianwei Zhang et al.

Transforming large deep neural network (DNN) models into the multi-exit architectures can overcome the overthinking issue and distribute a large DNN model on resource-constrained scenarios (e.g. IoT frontend devices and backend servers) for inference and transmission efficiency. Nevertheless, intellectual property (IP) protection for the multi-exit models in the wild is still an unsolved challenge. Previous efforts to verify DNN model ownership mainly rely on querying the model with specific samples and checking the responses, e.g., DNN watermarking and fingerprinting. However, they are vulnerable to adversarial settings such as adversarial training and are not suitable for the IP verification for multi-exit DNN models. In this paper, we propose a novel approach to fingerprint multi-exit models via inference time rather than inference predictions. Specifically, we design an effective method to generate a set of fingerprint samples to craft the inference process with a unique and robust inference time cost as the evidence for model ownership. We conduct extensive experiments to prove the uniqueness and robustness of our method on three structures (ResNet-56, VGG-16, and MobileNet) and three datasets (CIFAR-10, CIFAR-100, and Tiny-ImageNet) under comprehensive adversarial settings.

Shaofeng Li, Hui Liu, Tian Dong et al.

Natural language processing (NLP) systems have been proven to be vulnerable to backdoor attacks, whereby hidden features (backdoors) are trained into a language model and may only be activated by specific inputs (called triggers), to trick the model into producing unexpected behaviors. In this paper, we create covert and natural triggers for textual backdoor attacks, \textit{hidden backdoors}, where triggers can fool both modern language models and human inspection. We deploy our hidden backdoors through two state-of-the-art trigger embedding methods. The first approach via homograph replacement, embeds the trigger into deep neural networks through the visual spoofing of lookalike character replacement. The second approach uses subtle differences between text generated by language models and real natural text to produce trigger sentences with correct grammar and high fluency. We demonstrate that the proposed hidden backdoors can be effective across three downstream security-critical NLP tasks, representative of modern human-centric NLP systems, including toxic comment detection, neural machine translation (NMT), and question answering (QA). Our two hidden backdoor attacks can achieve an Attack Success Rate (ASR) of at least $97\%$ with an injection rate of only $3\%$ in toxic comment detection, $95.1\%$ ASR in NMT with less than $0.5\%$ injected data, and finally $91.12\%$ ASR against QA updated with only 27 poisoning data samples on a model previously trained with 92,024 samples (0.029\%). We are able to demonstrate the adversary's high success rate of attacks, while maintaining functionality for regular users, with triggers inconspicuous by the human administrators.

Xiaoying Wang, Shugong Zhang, Tian Dong

For the last almost three decades, since the famous Buchberger-Möller(BM) algorithm emerged, there has been wide interest in vanishing ideals of points and associated interpolation polynomials. Our paradigm is based on the theory of bivariate polynomial interpolation on cartesian point sets that gives us related degree reducing interpolation monomial and Newton bases directly. Since the bases are involved in the computation process as well as contained in the final output of BM algorithm, our paradigm obviously simplifies the computation and accelerates the BM process. The experiments show that the paradigm is best suited for the computation over finite prime fields that have many applications.