Backdoors implanted in pre-trained language models (PLMs) can be transferred to various downstream tasks, which exposes a severe security threat. However, most existing backdoor attacks against PLMs are un-targeted and task-specific. Few targeted and task-agnostic methods use manually pre-defined triggers and output representations, which prevent the attacks from being more effective and general. In this paper, we first summarize the requirements that a more threatening backdoor attack against PLMs should satisfy, and then propose a new backdoor attack method called UOR, which breaks the bottleneck of the previous approach by turning manual selection into automatic optimization. Specifically, we define poisoned supervised contrastive learning which can automatically learn the more uniform and universal output representations of triggers for various PLMs. Moreover, we use gradient search to select appropriate trigger words which can be adaptive to different PLMs and vocabularies. Experiments show that our method can achieve better attack performance on various text classification tasks compared to manual methods. Further, we tested our method on PLMs with different architectures, different usage paradigms, and more difficult tasks, which demonstrated the universality of our method.
相關內容
Deep neural networks (DNNs) have demonstrated remarkable performance across various tasks, including image and speech recognition. However, maximizing the effectiveness of DNNs requires meticulous optimization of numerous hyperparameters and network parameters through training. Moreover, high-performance DNNs entail many parameters, which consume significant energy during training. In order to overcome these challenges, researchers have turned to spiking neural networks (SNNs), which offer enhanced energy efficiency and biologically plausible data processing capabilities, rendering them highly suitable for sensory data tasks, particularly in neuromorphic data. Despite their advantages, SNNs, like DNNs, are susceptible to various threats, including adversarial examples and backdoor attacks. Yet, the field of SNNs still needs to be explored in terms of understanding and countering these attacks. This paper delves into backdoor attacks in SNNs using neuromorphic datasets and diverse triggers. Specifically, we explore backdoor triggers within neuromorphic data that can manipulate their position and color, providing a broader scope of possibilities than conventional triggers in domains like images. We present various attack strategies, achieving an attack success rate of up to 100\% while maintaining a negligible impact on clean accuracy. Furthermore, we assess these attacks' stealthiness, revealing that our most potent attacks possess significant stealth capabilities. Lastly, we adapt several state-of-the-art defenses from the image domain, evaluating their efficacy on neuromorphic data and uncovering instances where they fall short, leading to compromised performance.
Previous research has shown that federated learning (FL) systems are exposed to an array of security risks. Despite the proposal of several defensive strategies, they tend to be non-adaptive and specific to certain types of attacks, rendering them ineffective against unpredictable or adaptive threats. This work models adversarial federated learning as a Bayesian Stackelberg Markov game (BSMG) to capture the defender's incomplete information of various attack types. We propose meta-Stackelberg learning (meta-SL), a provably efficient meta-learning algorithm, to solve the equilibrium strategy in BSMG, leading to an adaptable FL defense. We demonstrate that meta-SL converges to the first-order $\varepsilon$-equilibrium point in $O(\varepsilon^{-2})$ gradient iterations, with $O(\varepsilon^{-4})$ samples needed per iteration, matching the state of the art. Empirical evidence indicates that our meta-Stackelberg framework performs exceptionally well against potent model poisoning and backdoor attacks of an uncertain nature.
Deep neural networks have a wide range of applications in solving various real-world tasks and have achieved satisfactory results, in domains such as computer vision, image classification, and natural language processing. Meanwhile, the security and robustness of neural networks have become imperative, as diverse researches have shown the vulnerable aspects of neural networks. Case in point, in Natural language processing tasks, the neural network may be fooled by an attentively modified text, which has a high similarity to the original one. As per previous research, most of the studies are focused on the image domain; Different from image adversarial attacks, the text is represented in a discrete sequence, traditional image attack methods are not applicable in the NLP field. In this paper, we propose a word-level NLP sentiment classifier attack model, which includes a self-attention mechanism-based word selection method and a greedy search algorithm for word substitution. We experiment with our attack model by attacking GRU and 1D-CNN victim models on IMDB datasets. Experimental results demonstrate that our model achieves a higher attack success rate and more efficient than previous methods due to the efficient word selection algorithms are employed and minimized the word substitute number. Also, our model is transferable, which can be used in the image domain with several modifications.
As LLMs become commonplace, machine-generated text has the potential to flood the internet with spam, social media bots, and valueless content. Watermarking is a simple and effective strategy for mitigating such harms by enabling the detection and documentation of LLM-generated text. Yet a crucial question remains: How reliable is watermarking in realistic settings in the wild? There, watermarked text may be modified to suit a user's needs, or entirely rewritten to avoid detection. We study the robustness of watermarked text after it is re-written by humans, paraphrased by a non-watermarked LLM, or mixed into a longer hand-written document. We find that watermarks remain detectable even after human and machine paraphrasing. While these attacks dilute the strength of the watermark, paraphrases are statistically likely to leak n-grams or even longer fragments of the original text, resulting in high-confidence detections when enough tokens are observed. For example, after strong human paraphrasing the watermark is detectable after observing 800 tokens on average, when setting a 1e-5 false positive rate. We also consider a range of new detection schemes that are sensitive to short spans of watermarked text embedded inside a large document, and we compare the robustness of watermarking to other kinds of detectors.
ML models are known to be vulnerable to adversarial query attacks. In these attacks, queries are iteratively perturbed towards a particular class without any knowledge of the target model besides its output. The prevalence of remotely-hosted ML classification models and Machine-Learning-as-a-Service platforms means that query attacks pose a real threat to the security of these systems. To deal with this, stateful defenses have been proposed to detect query attacks and prevent the generation of adversarial examples by monitoring and analyzing the sequence of queries received by the system. Several stateful defenses have been proposed in recent years. However, these defenses rely solely on similarity or out-of-distribution detection methods that may be effective in other domains. In the malware detection domain, the methods to generate adversarial examples are inherently different, and therefore we find that such detection mechanisms are significantly less effective. Hence, in this paper, we present MalProtect, which is a stateful defense against query attacks in the malware detection domain. MalProtect uses several threat indicators to detect attacks. Our results show that it reduces the evasion rate of adversarial query attacks by 80+\% in Android and Windows malware, across a range of attacker scenarios. In the first evaluation of its kind, we show that MalProtect outperforms prior stateful defenses, especially under the peak adversarial threat.
Ranking documents using Large Language Models (LLMs) by directly feeding the query and candidate documents into the prompt is an interesting and practical problem. However, there has been limited success so far, as researchers have found it difficult to outperform fine-tuned baseline rankers on benchmark datasets. We analyze pointwise and listwise ranking prompts used by existing methods and argue that off-the-shelf LLMs do not fully understand these ranking formulations, possibly due to the nature of how LLMs are trained. In this paper, we propose to significantly reduce the burden on LLMs by using a new technique called Pairwise Ranking Prompting (PRP). Our results are the first in the literature to achieve state-of-the-art ranking performance on standard benchmarks using moderate-sized open-sourced LLMs. On TREC-DL2020, PRP based on the Flan-UL2 model with 20B parameters outperforms the previous best approach in the literature, which is based on the blackbox commercial GPT-4 that has 50x (estimated) model size, by over 5% at NDCG@1. On TREC-DL2019, PRP is only inferior to the GPT-4 solution on the NDCG@5 and NDCG@10 metrics, while outperforming other existing solutions, such as InstructGPT which has 175B parameters, by over 10% for nearly all ranking metrics. Furthermore, we propose several variants of PRP to improve efficiency and show that it is possible to achieve competitive results even with linear complexity. We also discuss other benefits of PRP, such as supporting both generation and scoring LLM APIs, as well as being insensitive to input ordering.
In the past few years, the emergence of pre-training models has brought uni-modal fields such as computer vision (CV) and natural language processing (NLP) to a new era. Substantial works have shown they are beneficial for downstream uni-modal tasks and avoid training a new model from scratch. So can such pre-trained models be applied to multi-modal tasks? Researchers have explored this problem and made significant progress. This paper surveys recent advances and new frontiers in vision-language pre-training (VLP), including image-text and video-text pre-training. To give readers a better overall grasp of VLP, we first review its recent advances from five aspects: feature extraction, model architecture, pre-training objectives, pre-training datasets, and downstream tasks. Then, we summarize the specific VLP models in detail. Finally, we discuss the new frontiers in VLP. To the best of our knowledge, this is the first survey on VLP. We hope that this survey can shed light on future research in the VLP field.
Large-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved great success and become a milestone in the field of artificial intelligence (AI). Owing to sophisticated pre-training objectives and huge model parameters, large-scale PTMs can effectively capture knowledge from massive labeled and unlabeled data. By storing knowledge into huge parameters and fine-tuning on specific tasks, the rich knowledge implicitly encoded in huge parameters can benefit a variety of downstream tasks, which has been extensively demonstrated via experimental verification and empirical analysis. It is now the consensus of the AI community to adopt PTMs as backbone for downstream tasks rather than learning models from scratch. In this paper, we take a deep look into the history of pre-training, especially its special relation with transfer learning and self-supervised learning, to reveal the crucial position of PTMs in the AI development spectrum. Further, we comprehensively review the latest breakthroughs of PTMs. These breakthroughs are driven by the surge of computational power and the increasing availability of data, towards four important directions: designing effective architectures, utilizing rich contexts, improving computational efficiency, and conducting interpretation and theoretical analysis. Finally, we discuss a series of open problems and research directions of PTMs, and hope our view can inspire and advance the future study of PTMs.
Adversarial attack is a technique for deceiving Machine Learning (ML) models, which provides a way to evaluate the adversarial robustness. In practice, attack algorithms are artificially selected and tuned by human experts to break a ML system. However, manual selection of attackers tends to be sub-optimal, leading to a mistakenly assessment of model security. In this paper, a new procedure called Composite Adversarial Attack (CAA) is proposed for automatically searching the best combination of attack algorithms and their hyper-parameters from a candidate pool of \textbf{32 base attackers}. We design a search space where attack policy is represented as an attacking sequence, i.e., the output of the previous attacker is used as the initialization input for successors. Multi-objective NSGA-II genetic algorithm is adopted for finding the strongest attack policy with minimum complexity. The experimental result shows CAA beats 10 top attackers on 11 diverse defenses with less elapsed time (\textbf{6 $\times$ faster than AutoAttack}), and achieves the new state-of-the-art on $l_{\infty}$, $l_{2}$ and unrestricted adversarial attacks.
Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), such that the attacked model performs well on benign samples, whereas its prediction will be maliciously changed if the hidden backdoor is activated by the attacker-defined trigger. Backdoor attack could happen when the training process is not fully controlled by the user, such as training on third-party datasets or adopting third-party models, which poses a new and realistic threat. Although backdoor learning is an emerging and rapidly growing research area, its systematic review, however, remains blank. In this paper, we present the first comprehensive survey of this realm. We summarize and categorize existing backdoor attacks and defenses based on their characteristics, and provide a unified framework for analyzing poisoning-based backdoor attacks. Besides, we also analyze the relation between backdoor attacks and the relevant fields ($i.e.,$ adversarial attack and data poisoning), and summarize the benchmark datasets. Finally, we briefly outline certain future research directions relying upon reviewed works.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191