CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models

Backdoors can be injected into NLP models to induce misbehavior when the input text contains a specific feature, known as a trigger, which the attacker secretly selects. Unlike fixed words, phrases, or sentences used in the static text trigger, NLP dynamic backdoor attacks design triggers associated with abstract and latent text features, making them considerably stealthier than traditional static backdoor attacks. However, existing research on NLP backdoor detection primarily focuses on defending against static backdoor attacks, while detecting dynamic backdoors in NLP models remains largely unexplored. This paper presents CLIBE, the first framework to detect dynamic backdoors in Transformer-based NLP models. CLIBE injects a "few-shot perturbation" into the suspect Transformer model by crafting optimized weight perturbation in the attention layers to make the perturbed model classify a limited number of reference samples as a target label. Subsequently, CLIBE leverages the generalization ability of this few-shot perturbation to determine whether the original model contains a dynamic backdoor. Extensive evaluation on three advanced NLP dynamic backdoor attacks, two widely-used Transformer frameworks, and four real-world classification tasks strongly validates the effectiveness of CLIBE. We also demonstrate the robustness of CLIBE against various adaptive attacks. Furthermore, we employ CLIBE to scrutinize 49 popular Transformer models on Hugging Face and discover one exhibiting a high probability of containing a dynamic backdoor. We have contacted Hugging Face and provided detailed evidence of this model's backdoor behavior. Moreover, we extend CLIBE to detect backdoor text generation models modified to exhibit toxic behavior. To the best of our knowledge, CLIBE is the first framework capable of detecting backdoors in text generation models without access to trigger input test samples.

Iterative or Innovative? A Problem-Oriented Perspective for Code Optimization

Large language models (LLMs) have demonstrated strong capabilities in solving a wide range of programming tasks. However, LLMs have rarely been explored for code optimization. In this paper, we explore code optimization with a focus on performance enhancement, specifically aiming to optimize code for minimal execution time. The recently proposed first PIE dataset for performance optimization constructs program optimization pairs based on iterative submissions from the same programmer for the same problem. However, this approach restricts LLMs to local performance improvements, neglecting global algorithmic innovation. Therefore, we adopt a completely different perspective by reconstructing the optimization pairs into a problem-oriented approach. This allows for the integration of various ingenious ideas from different programmers tackling the same problem. Experimental results demonstrate that adapting LLMs to problem-oriented optimization pairs significantly enhances their optimization capabilities. Meanwhile, we identified performance bottlenecks within the problem-oriented perspective. By employing model merge, we further overcame bottlenecks and ultimately elevated the program optimization ratio ($51.76\%\rightarrow76.65\%$) and speedup ($2.65\times\rightarrow5.09\times$) to new levels.

Uncovering LLM-Generated Code: A Zero-Shot Synthetic Code Detector via Code Rewriting

Large Language Models (LLMs) have exhibited remarkable proficiency in generating code. However, the misuse of LLM-generated (Synthetic) code has prompted concerns within both educational and industrial domains, highlighting the imperative need for the development of synthetic code detectors. Existing methods for detecting LLM-generated content are primarily tailored for general text and often struggle with code content due to the distinct grammatical structure of programming languages and massive "low-entropy" tokens. Building upon this, our work proposes a novel zero-shot synthetic code detector based on the similarity between the code and its rewritten variants. Our method relies on the intuition that the differences between the LLM-rewritten and original codes tend to be smaller when the original code is synthetic. We utilize self-supervised contrastive learning to train a code similarity model and assess our approach on two synthetic code detection benchmarks. Our results demonstrate a notable enhancement over existing synthetic content detectors designed for general texts, with an improvement of 20.5% in the APPS benchmark and 29.1% in the MBPP benchmark.

Emulating Full Client Participation: A Long-Term Client Selection Strategy for Federated Learning

Client selection significantly affects the system convergence efficiency and is a crucial problem in federated learning. Existing methods often select clients by evaluating each round individually and overlook the necessity for long-term optimization, resulting in suboptimal performance and potential fairness issues. In this study, we propose a novel client selection strategy designed to emulate the performance achieved with full client participation. In a single round, we select clients by minimizing the gradient-space estimation error between the client subset and the full client set. In multi-round selection, we introduce a novel individual fairness constraint, which ensures that clients with similar data distributions have similar frequencies of being selected. This constraint guides the client selection process from a long-term perspective. We employ Lyapunov optimization and submodular functions to efficiently identify the optimal subset of clients, and provide a theoretical analysis of the convergence ability. Experiments demonstrate that the proposed strategy significantly improves both accuracy and fairness compared to previous methods while also exhibiting efficiency by incurring minimal time overhead.

Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?

Transformer-based trajectory optimization methods have demonstrated exceptional performance in offline Reinforcement Learning (offline RL), yet it poses challenges due to substantial parameter size and limited scalability, which is particularly critical in sequential decision-making scenarios where resources are constrained such as in robots and drones with limited computational power. Mamba, a promising new linear-time sequence model, offers performance on par with transformers while delivering substantially fewer parameters on long sequences. As it remains unclear whether Mamba is compatible with trajectory optimization, this work aims to conduct comprehensive experiments to explore the potential of Decision Mamba in offline RL (dubbed DeMa) from the aspect of data structures and network architectures with the following insights: (1) Long sequences impose a significant computational burden without contributing to performance improvements due to the fact that DeMa's focus on sequences diminishes approximately exponentially. Consequently, we introduce a Transformer-like DeMa as opposed to an RNN-like DeMa. (2) For the components of DeMa, we identify that the hidden attention mechanism is key to its success, which can also work well with other residual structures and does not require position embedding. Extensive evaluations from eight Atari games demonstrate that our specially designed DeMa is compatible with trajectory optimization and surpasses previous state-of-the-art methods, outdoing Decision Transformer (DT) by 80\% with 30\% fewer parameters, and exceeds DT in MuJoCo with only a quarter of the parameters.

Could It Be Generated? Towards Practical Analysis of Memorization in Text-To-Image Diffusion Models

The past few years have witnessed substantial advancement in text-guided image generation powered by diffusion models. However, it was shown that text-to-image diffusion models are vulnerable to training image memorization, raising concerns on copyright infringement and privacy invasion. In this work, we perform practical analysis of memorization in text-to-image diffusion models. Targeting a set of images to protect, we conduct quantitive analysis on them without need to collect any prompts. Specifically, we first formally define the memorization of image and identify three necessary conditions of memorization, respectively similarity, existence and probability. We then reveal the correlation between the model's prediction error and image replication. Based on the correlation, we propose to utilize inversion techniques to verify the safety of target images against memorization and measure the extent to which they are memorized. Model developers can utilize our analysis method to discover memorized images or reliably claim safety against memorization. Extensive experiments on the Stable Diffusion, a popular open-source text-to-image diffusion model, demonstrate the effectiveness of our analysis method.

PRSA: Prompt Reverse Stealing Attacks against Large Language Models

Prompt, recognized as crucial intellectual property, enables large language models (LLMs) to perform specific tasks without the need of fine-tuning, underscoring their escalating importance. With the rise of prompt-based services, such as prompt marketplaces and LLM applications, providers often display prompts' capabilities through input-output examples to attract users. However, this paradigm raises a pivotal security concern: does the exposure of input-output pairs pose the risk of potential prompt leakage, infringing on the intellectual property rights of the developers? To our knowledge, this problem still has not been comprehensively explored yet. To remedy this gap, in this paper, we perform the first in depth exploration and propose a novel attack framework for reverse-stealing prompts against commercial LLMs, namely PRSA. The main idea of PRSA is that by analyzing the critical features of the input-output pairs, we mimic and gradually infer (steal) the target prompts. In detail, PRSA mainly consists of two key phases: prompt mutation and prompt pruning. In the mutation phase, we propose a prompt attention algorithm based on differential feedback to capture these critical features for effectively inferring the target prompts. In the prompt pruning phase, we identify and mask the words dependent on specific inputs, enabling the prompts to accommodate diverse inputs for generalization. Through extensive evaluation, we verify that PRSA poses a severe threat in real world scenarios. We have reported these findings to prompt service providers and actively collaborate with them to take protective measures for prompt copyright.

SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems

Recent advances in multi-agent reinforcement learning (MARL) have opened up vast application prospects, including swarm control of drones, collaborative manipulation by robotic arms, and multi-target encirclement. However, potential security threats during the MARL deployment need more attention and thorough investigation. Recent researches reveal that an attacker can rapidly exploit the victim's vulnerabilities and generate adversarial policies, leading to the victim's failure in specific tasks. For example, reducing the winning rate of a superhuman-level Go AI to around 20%. They predominantly focus on two-player competitive environments, assuming attackers possess complete global state observation. In this study, we unveil, for the first time, the capability of attackers to generate adversarial policies even when restricted to partial observations of the victims in multi-agent competitive environments. Specifically, we propose a novel black-box attack (SUB-PLAY), which incorporates the concept of constructing multiple subgames to mitigate the impact of partial observability and suggests the sharing of transitions among subpolicies to improve the exploitative ability of attackers. Extensive evaluations demonstrate the effectiveness of SUB-PLAY under three typical partial observability limitations. Visualization results indicate that adversarial policies induce significantly different activations of the victims' policy networks. Furthermore, we evaluate three potential defenses aimed at exploring ways to mitigate security threats posed by adversarial policies, providing constructive recommendations for deploying MARL in competitive environments.

The Risk of Federated Learning to Skew Fine-Tuning Features and Underperform Out-of-Distribution Robustness

To tackle the scarcity and privacy issues associated with domain-specific datasets, the integration of federated learning in conjunction with fine-tuning has emerged as a practical solution. However, our findings reveal that federated learning has the risk of skewing fine-tuning features and compromising the out-of-distribution robustness of the model. By introducing three robustness indicators and conducting experiments across diverse robust datasets, we elucidate these phenomena by scrutinizing the diversity, transferability, and deviation within the model feature space. To mitigate the negative impact of federated learning on model robustness, we introduce GNP, a \underline{G}eneral \underline{N}oisy \underline{P}rojection-based robust algorithm, ensuring no deterioration of accuracy on the target distribution. Specifically, the key strategy for enhancing model robustness entails the transfer of robustness from the pre-trained model to the fine-tuned model, coupled with adding a small amount of Gaussian noise to augment the representative capacity of the model. Comprehensive experimental results demonstrate that our approach markedly enhances the robustness across diverse scenarios, encompassing various parameter-efficient fine-tuning methods and confronting different levels of data heterogeneity.

MEAOD: Model Extraction Attack against Object Detectors

The widespread use of deep learning technology across various industries has made deep neural network models highly valuable and, as a result, attractive targets for potential attackers. Model extraction attacks, particularly query-based model extraction attacks, allow attackers to replicate a substitute model with comparable functionality to the victim model and present a significant threat to the confidentiality and security of MLaaS platforms. While many studies have explored threats of model extraction attacks against classification models in recent years, object detection models, which are more frequently used in real-world scenarios, have received less attention. In this paper, we investigate the challenges and feasibility of query-based model extraction attacks against object detection models and propose an effective attack method called MEAOD. It selects samples from the attacker-possessed dataset to construct an efficient query dataset using active learning and enhances the categories with insufficient objects. We additionally improve the extraction effectiveness by updating the annotations of the query dataset. According to our gray-box and black-box scenarios experiments, we achieve an extraction performance of over 70% under the given condition of a 10k query budget.