Exploring Gradient-Guided Masked Language Model to Detect Textual Adversarial Attacks

Textual adversarial examples pose serious threats to the reliability of natural language processing systems. Recent studies suggest that adversarial examples tend to deviate from the underlying manifold of normal texts, whereas pre-trained masked language models can approximate the manifold of normal data. These findings inspire the exploration of masked language models for detecting textual adversarial attacks. We first introduce Masked Language Model-based Detection (MLMD), leveraging the mask and unmask operations of the masked language modeling (MLM) objective to induce the difference in manifold changes between normal and adversarial texts. Although MLMD achieves competitive detection performance, its exhaustive one-by-one masking strategy introduces significant computational overhead. Our posterior analysis reveals that a significant number of non-keywords in the input are not important for detection but consume resources. Building on this, we introduce Gradient-guided MLMD (GradMLMD), which leverages gradient information to identify and skip non-keywords during detection, significantly reducing resource consumption without compromising detection performance.

Test-Time Backdoor Detection for Object Detection Models

Object detection models are vulnerable to backdoor attacks, where attackers poison a small subset of training samples by embedding a predefined trigger to manipulate prediction. Detecting poisoned samples (i.e., those containing triggers) at test time can prevent backdoor activation. However, unlike image classification tasks, the unique characteristics of object detection -- particularly its output of numerous objects -- pose fresh challenges for backdoor detection. The complex attack effects (e.g., "ghost" object emergence or "vanishing" object) further render current defenses fundamentally inadequate. To this end, we design TRAnsformation Consistency Evaluation (TRACE), a brand-new method for detecting poisoned samples at test time in object detection. Our journey begins with two intriguing observations: (1) poisoned samples exhibit significantly more consistent detection results than clean ones across varied backgrounds. (2) clean samples show higher detection consistency when introduced to different focal information. Based on these phenomena, TRACE applies foreground and background transformations to each test sample, then assesses transformation consistency by calculating the variance in objects confidences. TRACE achieves black-box, universal backdoor detection, with extensive experiments showing a 30% improvement in AUROC over state-of-the-art defenses and resistance to adaptive attacks.

Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimization

Deep neural networks (DNNs) are susceptible to universal adversarial perturbations (UAPs). These perturbations are meticulously designed to fool the target model universally across all sample classes. Unlike instance-specific adversarial examples (AEs), generating UAPs is more complex because they must be generalized across a wide range of data samples and models. Our research reveals that existing universal attack methods, which optimize UAPs using DNNs with static model parameter snapshots, do not fully leverage the potential of DNNs to generate more effective UAPs. Rather than optimizing UAPs against static DNN models with a fixed training set, we suggest using dynamic model-data pairs to generate UAPs. In particular, we introduce a dynamic maximin optimization strategy, aiming to optimize the UAP across a variety of optimal model-data pairs. We term this approach DM-UAP. DM-UAP utilizes an iterative max-min-min optimization framework that refines the model-data pairs, coupled with a curriculum UAP learning algorithm to examine the combined space of model parameters and data thoroughly. Comprehensive experiments on the ImageNet dataset demonstrate that the proposed DM-UAP markedly enhances both cross-sample universality and cross-model transferability of UAPs. Using only 500 samples for UAP generation, DM-UAP outperforms the state-of-the-art approach with an average increase in fooling ratio of 12.108%.

Not All Edges are Equally Robust: Evaluating the Robustness of Ranking-Based Federated Learning

Federated Ranking Learning (FRL) is a state-of-the-art FL framework that stands out for its communication efficiency and resilience to poisoning attacks. It diverges from the traditional FL framework in two ways: 1) it leverages discrete rankings instead of gradient updates, significantly reducing communication costs and limiting the potential space for malicious updates, and 2) it uses majority voting on the server side to establish the global ranking, ensuring that individual updates have minimal influence since each client contributes only a single vote. These features enhance the system's scalability and position FRL as a promising paradigm for FL training. However, our analysis reveals that FRL is not inherently robust, as certain edges are particularly vulnerable to poisoning attacks. Through a theoretical investigation, we prove the existence of these vulnerable edges and establish a lower bound and an upper bound for identifying them in each layer. Based on this finding, we introduce a novel local model poisoning attack against FRL, namely the Vulnerable Edge Manipulation (VEM) attack. The VEM attack focuses on identifying and perturbing the most vulnerable edges in each layer and leveraging an optimization-based approach to maximize the attack's impact. Through extensive experiments on benchmark datasets, we demonstrate that our attack achieves an overall 53.23% attack impact and is 3.7x more impactful than existing methods. Our findings highlight significant vulnerabilities in ranking-based FL systems and underline the urgency for the development of new robust FL frameworks.

Memorization in deep learning: A survey

Deep Learning (DL) powered by Deep Neural Networks (DNNs) has revolutionized various domains, yet understanding the intricacies of DNN decision-making and learning processes remains a significant challenge. Recent investigations have uncovered an interesting memorization phenomenon in which DNNs tend to memorize specific details from examples rather than learning general patterns, affecting model generalization, security, and privacy. This raises critical questions about the nature of generalization in DNNs and their susceptibility to security breaches. In this survey, we present a systematic framework to organize memorization definitions based on the generalization and security/privacy domains and summarize memorization evaluation methods at both the example and model levels. Through a comprehensive literature review, we explore DNN memorization behaviors and their impacts on security and privacy. We also introduce privacy vulnerabilities caused by memorization and the phenomenon of forgetting and explore its connection with memorization. Furthermore, we spotlight various applications leveraging memorization and forgetting mechanisms, including noisy label learning, privacy preservation, and model enhancement. This survey offers the first-in-kind understanding of memorization in DNNs, providing insights into its challenges and opportunities for enhancing AI development while addressing critical ethical concerns.

Large Language Model Watermark Stealing With Mixed Integer Programming

The Large Language Model (LLM) watermark is a newly emerging technique that shows promise in addressing concerns surrounding LLM copyright, monitoring AI-generated text, and preventing its misuse. The LLM watermark scheme commonly includes generating secret keys to partition the vocabulary into green and red lists, applying a perturbation to the logits of tokens in the green list to increase their sampling likelihood, thus facilitating watermark detection to identify AI-generated text if the proportion of green tokens exceeds a threshold. However, recent research indicates that watermarking methods using numerous keys are susceptible to removal attacks, such as token editing, synonym substitution, and paraphrasing, with robustness declining as the number of keys increases. Therefore, the state-of-the-art watermark schemes that employ fewer or single keys have been demonstrated to be more robust against text editing and paraphrasing. In this paper, we propose a novel green list stealing attack against the state-of-the-art LLM watermark scheme and systematically examine its vulnerability to this attack. We formalize the attack as a mixed integer programming problem with constraints. We evaluate our attack under a comprehensive threat model, including an extreme scenario where the attacker has no prior knowledge, lacks access to the watermark detector API, and possesses no information about the LLM's parameter settings or watermark injection/detection scheme. Extensive experiments on LLMs, such as OPT and LLaMA, demonstrate that our attack can successfully steal the green list and remove the watermark across all settings.

Detector Collapse: Backdooring Object Detection to Catastrophic Overload or Blindness

Object detection tasks, crucial in safety-critical systems like autonomous driving, focus on pinpointing object locations. These detectors are known to be susceptible to backdoor attacks. However, existing backdoor techniques have primarily been adapted from classification tasks, overlooking deeper vulnerabilities specific to object detection. This paper is dedicated to bridging this gap by introducing Detector Collapse} (DC), a brand-new backdoor attack paradigm tailored for object detection. DC is designed to instantly incapacitate detectors (i.e., severely impairing detector's performance and culminating in a denial-of-service). To this end, we develop two innovative attack schemes: Sponge for triggering widespread misidentifications and Blinding for rendering objects invisible. Remarkably, we introduce a novel poisoning strategy exploiting natural objects, enabling DC to act as a practical backdoor in real-world environments. Our experiments on different detectors across several benchmarks show a significant improvement ($\sim$10\%-60\% absolute and $\sim$2-7$\times$ relative) in attack efficacy over state-of-the-art attacks.

AGRAMPLIFIER: Defending Federated Learning Against Poisoning Attacks Through Local Update Amplification

The collaborative nature of federated learning (FL) poses a major threat in the form of manipulation of local training data and local updates, known as the Byzantine poisoning attack. To address this issue, many Byzantine-robust aggregation rules (AGRs) have been proposed to filter out or moderate suspicious local updates uploaded by Byzantine participants. This paper introduces a novel approach called AGRAMPLIFIER, aiming to simultaneously improve the robustness, fidelity, and efficiency of the existing AGRs. The core idea of AGRAMPLIFIER is to amplify the "morality" of local updates by identifying the most repressive features of each gradient update, which provides a clearer distinction between malicious and benign updates, consequently improving the detection effect. To achieve this objective, two approaches, namely AGRMP and AGRXAI, are proposed. AGRMP organizes local updates into patches and extracts the largest value from each patch, while AGRXAI leverages explainable AI methods to extract the gradient of the most activated features. By equipping AGRAMPLIFIER with the existing Byzantine-robust mechanisms, we successfully enhance the model's robustness, maintaining its fidelity and improving overall efficiency. AGRAMPLIFIER is universally compatible with the existing Byzantine-robust mechanisms. The paper demonstrates its effectiveness by integrating it with all mainstream AGR mechanisms. Extensive evaluations conducted on seven datasets from diverse domains against seven representative poisoning attacks consistently show enhancements in robustness, fidelity, and efficiency, with average gains of 40.08%, 39.18%, and 10.68%, respectively.

Client-side Gradient Inversion Against Federated Learning from Poisoning

Federated Learning (FL) enables distributed participants (e.g., mobile devices) to train a global model without sharing data directly to a central server. Recent studies have revealed that FL is vulnerable to gradient inversion attack (GIA), which aims to reconstruct the original training samples and poses high risk against the privacy of clients in FL. However, most existing GIAs necessitate control over the server and rely on strong prior knowledge including batch normalization and data distribution information. In this work, we propose Client-side poisoning Gradient Inversion (CGI), which is a novel attack method that can be launched from clients. For the first time, we show the feasibility of a client-side adversary with limited knowledge being able to recover the training samples from the aggregated global model. We take a distinct approach in which the adversary utilizes a malicious model that amplifies the loss of a specific targeted class of interest. When honest clients employ the poisoned global model, the gradients of samples belonging to the targeted class are magnified, making them the dominant factor in the aggregated update. This enables the adversary to effectively reconstruct the private input belonging to other clients using the aggregated update. In addition, our CGI also features its ability to remain stealthy against Byzantine-robust aggregation rules (AGRs). By optimizing malicious updates and blending benign updates with a malicious replacement vector, our method remains undetected by these defense mechanisms. To evaluate the performance of CGI, we conduct experiments on various benchmark datasets, considering representative Byzantine-robust AGRs, and exploring diverse FL settings with different levels of adversary knowledge about the data. Our results demonstrate that CGI consistently and successfully extracts training input in all tested scenarios.

Masked Language Model Based Textual Adversarial Example Detection

Adversarial attacks are a serious threat to the reliable deployment of machine learning models in safety-critical applications. They can misguide current models to predict incorrectly by slightly modifying the inputs. Recently, substantial work has shown that adversarial examples tend to deviate from the underlying data manifold of normal examples, whereas pre-trained masked language models can fit the manifold of normal NLP data. To explore how to use the masked language model in adversarial detection, we propose a novel textual adversarial example detection method, namely Masked Language Model-based Detection (MLMD), which can produce clearly distinguishable signals between normal examples and adversarial examples by exploring the changes in manifolds induced by the masked language model. MLMD features a plug and play usage (i.e., no need to retrain the victim model) for adversarial defense and it is agnostic to classification tasks, victim model's architectures, and to-be-defended attack methods. We evaluate MLMD on various benchmark textual datasets, widely studied machine learning models, and state-of-the-art (SOTA) adversarial attacks (in total $3*4*4 = 48$ settings). Experimental results show that MLMD can achieve strong performance, with detection accuracy up to 0.984, 0.967, and 0.901 on AG-NEWS, IMDB, and SST-2 datasets, respectively. Additionally, MLMD is superior, or at least comparable to, the SOTA detection defenses in detection accuracy and F1 score. Among many defenses based on the off-manifold assumption of adversarial examples, this work offers a new angle for capturing the manifold change. The code for this work is openly accessible at \url{https://github.com/mlmddetection/MLMDdetection}.