Black-Box Adversarial Attacks

Overview

Black-box adversarial attacks ask how an attacker can cause an AI system to misclassify, produce unsafe output, or take an unwanted action without access to its internal parameters or gradients. Methods use feedback from model queries—such as labels, scores, or responses—with decision-boundary search, finite differences, bandits, evolutionary or reinforcement-learning optimization; others craft perturbations on surrogate models and rely on transfer to unseen targets. Work spans images and physical patches, text and jailbreak prompts, audio, graphs, malware detectors, and tool-using or multimodal agents, often under constraints such as limited queries, imperceptibility, and preserving input meaning or function. Key tensions include whether attacks transfer across architectures and real-world transformations, how to compare them under fair query budgets, and whether defenses can resist adaptive attacks without sacrificing clean performance or utility.

Latest papers

189 papers15 papers in the last four weeks, down 17% on the four weeks before. 0.1% of all new papers.

Sep 9, 2025

Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems

Voice Authentication Systems (VAS) use unique vocal characteristics for verification. They are increasingly integrated into high-security sectors such as banking and healthcare. Despite their improvements using deep learning, they face severe vulnerabilities from sophisticated threats like deepfakes and adversarial attacks. The emergence of realistic voice cloning complicates detection, as systems struggle to distinguish authentic from synthetic audio. While anti-spoofing countermeasures (CMs) exist to mitigate these risks, many rely on static detection models that can be bypassed by novel adversarial methods, leaving a critical security gap. To demonstrate this vulnerability, we propose the Spectral Masking and Interpolation Attack (SMIA), a novel method that strategically manipulates inaudible frequency regions of AI-generated audio. By altering the voice in imperceptible zones to the human ear, SMIA creates adversarial samples that sound authentic while deceiving CMs. We conducted a comprehensive evaluation of our attack against state-of-the-art (SOTA) models across multiple tasks, under simulated real-world conditions. SMIA achieved a strong attack success rate (ASR) of at least 82% against combined VAS/CM systems, at least 97.5% against standalone speaker verification systems, and 100% against countermeasures. These findings conclusively demonstrate that current security postures are insufficient against adaptive adversarial attacks. This work highlights the urgent need for a paradigm shift toward next-generation defenses that employ dynamic, context-aware frameworks capable of evolving with the threat landscape.
Aug 12, 2025

Constrained Black-Box Attacks Against Cooperative Multi-Agent Reinforcement Learning

Collaborative multi-agent reinforcement learning (MARL) is increasingly deployed in critical domains, yet its vulnerability to adversarial perturbations has not been thoroughly investigated. Most existing adversarial attacks against MARL rely on optimistic assumptions, such as access to policy weights or the ability to train surrogate policies. We investigate whether adversaries with limited capabilities remain effective against MARL agents. In particular, we study two restricted attack settings that are overlooked in the literature: (i) adversaries with access only to agent observations and (ii) adversaries with no access whatsoever. Our approach generates perturbations that intentionally misalign how victim agents perceive their environment, preventing them from collaborating. We conduct extensive experiments across a diverse set of 22 environments. Our results demonstrate both the effectiveness and sample efficiency of our attacks.
Jun 30, 2025

Consensus-based optimization for closed-box adversarial attacks and a connection to evolution strategies

Consensus-based optimization (CBO) has established itself as an efficient gradient-free optimization scheme, with attractive mathematical properties, such as mean-field convergence results for non-convex loss functions. In this work, we study CBO in the context of closed-box adversarial attacks, which are imperceptible input perturbations that aim to fool a classifier, without accessing its gradient. Our contribution is to establish a connection between the so-called consensus hopping as introduced by Riedl et al. and natural evolution strategies (NES) commonly applied in the context of adversarial attacks and to rigorously relate both methods to gradient-based optimization schemes. Beyond that, we provide a comprehensive experimental study that shows that despite the conceptual similarities, CBO can outperform NES and other evolutionary strategies in certain scenarios.
Jun 8, 2025

HauntAttack: When Attack Follows Reasoning as a Shadow

Emerging Large Reasoning Models (LRMs) consistently excel in mathematical and reasoning tasks, showcasing remarkable capabilities. However, the enhancement of reasoning abilities and the exposure of internal reasoning processes introduce new safety vulnerabilities. A critical question arises: when reasoning becomes intertwined with harmfulness, will LRMs become more vulnerable to jailbreaks in reasoning mode? To investigate this, we introduce HauntAttack, a novel and general-purpose black-box adversarial attack framework that systematically embeds harmful instructions into reasoning questions. Specifically, we modify key reasoning conditions in existing questions with harmful instructions, thereby constructing a reasoning pathway that guides the model step by step toward unsafe outputs. We evaluate HauntAttack on 11 LRMs and observe an average attack success rate of over 70%, achieving up to 13 percentage points of absolute improvement over the strongest prior baseline. Our further analysis reveals that even advanced safety-aligned models remain highly susceptible to reasoning-based attacks, offering insights into the urgent challenge of balancing reasoning capability and safety in future model development.
Feb 6, 2025

How Vulnerable Is My Learned Policy? Universal Adversarial Perturbation Attacks On Modern Behavior Cloning Policies

Imitation learning, also known as learning from demonstrations, is a popular approach to train AI models; however, the vulnerability of these models to adversarial attacks remains underexplored. We present the first systematic study of adversarial attacks, across a range of both classic and recently proposed imitation learning algorithms, including Vanilla Behavior Cloning (Vanilla BC), LSTM-GMM, Implicit Behavior Cloning (IBC), Diffusion Policy (DP), and Vector-Quantized Behavior Transformer (VQ-BET). We study the vulnerability of these methods to white-box, grey-box and black-box adversarial perturbations. Our experiments reveal that most existing methods are highly vulnerable to these attacks, including black-box transfer attacks that transfer across algorithms. White-box attacks cause at least a 65% reduction in average task success across all evaluated tasks and algorithms, while the black-box transfer attacks reduce task success by up to 88% on Lift, 99% on Can, and 100% on Square. To the best of our knowledge, we are the first to study and compare the vulnerabilities of different popular imitation learning algorithms to both white-box and black-box attacks. Our findings highlight the vulnerabilities of modern imitation learning algorithms, paving the way for future work in addressing such limitations. Videos and code are available at https://sites.google.com/view/uap-attacks-on-bc.
Oct 2, 2024

Adversarial Robustness of AI-Generated Image Detectors in the Real World

The rapid advancement of Generative Artificial Intelligence (GenAI) capabilities is accompanied by a concerning rise in its misuse. In particular the generation of credible misinformation in the form of images poses a significant threat to the public trust in democratic processes. Consequently, there is an urgent need to develop tools to reliably distinguish between authentic and AI-generated content. The majority of detection methods are based on neural networks that are trained to recognize forensic artifacts. In this work, we demonstrate that current state-of-the-art classifiers are vulnerable to adversarial examples under real-world conditions. Through extensive experiments, comprising four detection methods and five attack algorithms, we show that an attacker can dramatically decrease classification performance, without internal knowledge of the detector's architecture. Notably, most attacks remain effective even when images are degraded during the upload to, e.g., social media platforms. In a case study, we demonstrate that these robustness challenges are also found in commercial tools by conducting black-box attacks on HIVE, a proprietary online GenAI media detector. In addition, we evaluate the robustness of using generated features of a robust pre-trained model and showed that this increases the robustness, while not reaching the performance on benign inputs. These results, along with the increasing potential of GenAI to erode public trust, underscore the need for more research and new perspectives on methods to prevent its misuse.
Apr 1, 2024

Perturbation Effects on Robustness and Individual Fairness

Deep neural networks are vulnerable to adversarial perturbations that can simultaneously degrade prediction robustness and individual fairness across diverse application settings. However, existing evaluation protocols typically assess these dimensions in isolation, thereby obscuring critical failure modes. To bridge this gap, we formalize Robust Individual Fairness (RIF): under semantic-preserving (truth-condition-preserving) perturbations, predictions should remain both correct with respect to the ground truth and invariant across semantically equivalent individuals. To surface RIF violations in practice, we introduce RIFair, a black-box adversarial framework that leverages a decoupled perturbation strategy to construct semantically preserved yet unrobust and/or unfair instance pairs. Experiments across multiple model architectures and real-world textual datasets show that robustness-only or fairness-only metrics often miss Robust Biased and Unrobust Fair behaviors. RIFair}reliably exposes these hidden vulnerabilities, supporting RIF as a necessary criterion for trustworthy model assessment. The experimental code is publicly available at https://github.com/Xuran-LI/RIFair.
Feb 6, 2024

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

Recent advancements in multi-agent reinforcement learning (MARL) have opened up vast application prospects, such as 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 research reveals that attackers can rapidly exploit the victim's vulnerabilities, generating adversarial policies that result in the failure of specific tasks. For instance, reducing the winning rate of a superhuman-level Go AI to around 20%. Existing studies 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) that incorporates the concept of constructing multiple subgames to mitigate the impact of partial observability and suggests sharing transitions among subpolicies to improve attackers' exploitative ability. 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.
Dec 4, 2023

InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models

Large vision-language models (LVLMs) have demonstrated their incredible capability in visual question answering. However, this rich visual interaction also makes LVLMs vulnerable to adversarial examples. In this paper, we formulate a novel and practical targeted attack scenario that the adversary knows only the vision encoder of the victim LVLM, without the knowledge of its prompts and its underlying large language model. This practical setting poses challenges to the cross-prompt and cross-model transferability of targeted adversarial attack, which aims to confuse the LVLM to output a response that is semantically similar to the attacker's chosen target text. To this end, we propose an instruction-tuned targeted attack (dubbed InstructTA) to deliver the targeted adversarial attack on LVLMs with high transferability. Initially, we utilize a public text-to-image generative model to reverse the target response into a target image, and employ GPT-4 to infer a reasonable instruction p′\boldsymbol{p}^\prime from the target response. We then form a local surrogate model (sharing the same vision encoder with the victim LVLM) to extract instruction-aware features of an adversarial image example and the target image, and minimize the distance between these two features to optimize the adversarial example. To further improve the transferability with instruction tuning, we augment the instruction p′\boldsymbol{p}^\prime with instructions paraphrased from GPT-4. Extensive experiments on 6 victim LVLMs demonstrate the superiority of our proposed method in targeted attack performance and transferability. In particular, InstructTA achieves an attack success rate of 51.9% on BLIP-2, outperforming the strongest baseline by 10.5%, and consistently yields the highest attack success rates across all evaluated models. The code is available at https://github.com/xunguangwang/InstructTA.