Machine learning classifiers are critically prone to evasion attacks. Adversarial examples are slightly modified inputs that are then misclassified, while remaining perceptively close to their originals. Last couple of years have witnessed a striking decrease in the amount of queries a black box attack submits to the target classifier, in order to forge adversarials. This particularly concerns the black-box score-based setup, where the attacker has access to top predicted probabilites: the amount of queries went from to millions of to less than a thousand. This paper presents SurFree, a geometrical approach that achieves a similar drastic reduction in the amount of queries in the hardest setup: black box decision-based attacks (only the top-1 label is available). We first highlight that the most recent attacks in that setup, HSJA, QEBA and GeoDA all perform costly gradient surrogate estimations. SurFree proposes to bypass these, by instead focusing on careful trials along diverse directions, guided by precise indications of geometrical properties of the classifier decision boundaries. We motivate this geometric approach before performing a head-to-head comparison with previous attacks with the amount of queries as a first class citizen. We exhibit a faster distortion decay under low query amounts (few hundreds to a thousand), while remaining competitive at higher query budgets.
A recent line of work on black-box adversarial attacks has revived the use of transfer from surrogate models by integrating it into query-based search. However, we find that existing approaches of this type underperform their potential, and can be overly complicated besides. Here, we provide a short and simple algorithm which achieves state-of-the-art results through a search which uses the surrogate network's class-score gradients, with no need for other priors or heuristics. The guiding assumption of the algorithm is that the studied networks are in a fundamental sense learning similar funct…
Shanghai Jiao Tong University（上海交通大学）；MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University（上海交通大学人工智能研究院教育部人工智能重点实验室）
This paper addresses the challenging black-box adversarial attack problem, where only classification confidence of a victim model is available. Inspired by consistency of visual saliency between different vision models, a surrogate model is expected to improve the attack performance via transferability. By combining transferability-based and query-based black-box attack, we propose a surprisingly simple baseline approach (named SimBA++) using the surrogate model, which significantly outperforms several state-of-the-art methods. Moreover, to efficiently utilize the query feedback, we update the…
MF-CLIP: Leveraging CLIP as Surrogate Models for No-box Adversarial Attacks
Hong Kong University of Science and Technology（香港科技大学）；University of Naples Federico II（那不勒斯费德里科二世大学）；Singapore Management University（新加坡管理大学）；Beijing Jiaotong University（北京交通大学）；National Lab of Pattern Recognition（模式识别国家重点实验室）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；School of Data Science, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）数据科学学院）；Shenzhen Research Institute of Big Data（深圳大数据研究院）；Tencent AI Lab（腾讯人工智能实验室）
This work studies black-box adversarial attacks against deep neural networks (DNNs), where the attacker can only access the query feedback returned by the attacked DNN model, while other information such as model parameters or the training datasets are unknown. One promising approach to improve attack performance is utilizing the adversarial transferability between some white-box surrogate models and the target model (i.e., the attacked model). However, due to the possible differences on model architectures and training datasets between surrogate and target models, dubbed "surrogate biases", t…
JD Technology（京东科技）；University of California, Los Angeles（加州大学洛杉矶分校）
We consider adversarial attacks to a black-box model when no queries are allowed. In this setting, many methods directly attack surrogate models and transfer the obtained adversarial examples to fool the target model. Plenty of previous works investigated what kind of attacks to the surrogate model can generate more transferable adversarial examples, but their performances are still limited due to the mismatches between surrogate models and the target model. In this paper, we tackle this problem from a novel angle -- instead of using the original surrogate models, can we obtain a Meta-Surrogat…
Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior
Tsinghua University（清华大学）；JQ Investments（JQ投资）；Academy of Mathematics and Systems Science, Chinese Academy of Sciences（中国科学院数学与系统科学研究院）；University of Chinese Academy of Sciences（中国科学院大学）；RealAI；Kaiyuan International Mathematical Sciences Institute（开源国际数学科学研究院）
Privacy-preserving Universal Adversarial Defense for Black-box Models
School of Cyber Science and Engineering, Wuhan University（武汉大学网络科学与工程学院）；City University of Hong Kong (CityU)（香港城市大学）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）
We consider the black-box adversarial setting, where the adversary has to generate adversarial perturbations without access to the target models to compute gradients. Previous methods tried to approximate the gradient either by using a transfer gradient of a surrogate white-box model, or based on the query feedback. However, these methods often suffer from low attack success rates or poor query efficiency since it is non-trivial to estimate the gradient in a high-dimensional space with limited information. To address these problems, we propose a prior-guided random gradient-free (P-RGF) method…
Do Defenses Against LLM Extraction Work Across Attacks? A Lifecycle Benchmark of Black-Box Model Extraction
Florida State University（佛罗里达州立大学）；Brigham Young University（杨百翰大学）；University of Michigan, Ann Arbor（密歇根大学安娜堡分校）；State University of New York at Buffalo（纽约州立大学布法罗分校）；Wake Forest University（维克森林大学）；University of Georgia（佐治亚大学）
Graph edge perturbations are dedicated to damaging the prediction of graph neural networks by modifying the graph structure. Previous gray-box attackers employ gradients from the surrogate model to locate the vulnerable edges to perturb the graph structure. However, unreliability exists in gradients on graph structures, which is rarely studied by previous works. In this paper, we discuss and analyze the errors caused by the unreliability of the structural gradients. These errors arise from rough gradient usage due to the discreteness of the graph structure and from the unreliability in the met…
Beijing Institute of Technology（北京理工大学）；Beijing Institute of Technology Chongqing Innovation Center（北京理工大学重庆创新中心）
Deep neural networks (DNNs) have achieved remarkable success in diverse fields. However, it has been demonstrated that DNNs are very vulnerable to adversarial examples even in black-box settings. A large number of black-box attack methods have been proposed to in the literature. However, those methods usually suffer from low success rates and large query counts, which cannot fully satisfy practical purposes. In this paper, we propose a hybrid attack method which trains meta adversarial perturbations (MAPs) on surrogate models and performs black-box attacks by estimating gradients of the models…
Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization
Key Laboratory of Symbolic Computation and Knowledge Engineering, MoE, Jilin University（符号计算与知识工程重点实验室，MoE，吉林大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
Deep Neural Networks (DNNs) are acknowledged as vulnerable to adversarial attacks, while the existing black-box attacks require extensive queries on the victim DNN to achieve high success rates. For query-efficiency, surrogate models of the victim are used to generate transferable Adversarial Examples (AEs) because of their Gradient Similarity (GS), i.e., surrogates' attack gradients are similar to the victim's ones. However, it is generally neglected to exploit their similarity on outputs, namely the Prediction Similarity (PS), to filter out inefficient queries by surrogates without querying …
