Vision-language models (VLMs) are increasingly deployed as trusted authorities -- fact-checking images on social media, comparing products, and moderating content. Users implicitly trust that these systems perceive the same visual content as they do. We show that adversarial examples break this assumption, enabling \emph{AI authority laundering}: an attacker subtly perturbs an image so that the VLM produces confident and authoritative responses about the \emph{wrong} input. Unlike jailbreaks or prompt injections, our attacks do not compromise model alignment; the attack operates entirely at the perceptual level. We demonstrate that standard attacks against publicly available CLIP models transfer reliably to production VLMs -- including GPT-5.4, Claude Opus4.6, Gemini3, and Grok~4.2. Across four attack surfaces, we show that authority laundering can amplify misinformation, disparage individuals, evade content moderation, and manipulate product recommendations. Our attacks have high success rates: In hundreds of attacks targeting identity manipulation and NSFW evasion, we measure success rates of 22−100% across six models. No novel attack algorithm is required: basic techniques known for over a decade suffice, establishing a lower bound on attacker capability that should concern defenders. Our results demonstrate that visual adversarial robustness is now a practical -- and still largely unsolved -- safety problem.
The visual modality of vision-language models (VLMs) is an underexplored attack surface for bypassing safety alignment. We introduce four jailbreak attacks exploiting the vision component: (1) encoding harmful instructions as visual symbol sequences with a decoding legend, (2) replacing harmful objects with benign substitutes (e.g., bomb -> banana) then prompting for harmful actions using the substitute term, (3) replacing harmful text in images (e.g., on book covers) with benign words while visual context preserves the original meaning, and (4) visual analogy puzzles whose solution requires inferring a prohibited concept. Evaluating across six frontier VLMs, our visual attacks bypass safety alignment and expose a cross-modality alignment gap: text-based safety training does not automatically generalize to harmful intent conveyed visually. For example, our visual cipher achieves 40.9% attack success on Claude-Haiku-4.5 versus 10.7% for an equivalent textual cipher. To further our insight into the attack mechanism, we present preliminary interpretability and mitigation results. These findings highlight that robust VLM alignment requires treating vision as a first-class target for safety post-training.
Vision-Language Models (VLMs) are now a core part of modern AI. Recent work proposed several visual jailbreak attacks using single/ holistic images. However, contemporary VLMs demonstrate strong robustness against such attacks due to extensive safety alignment through preference optimization, e.g., reinforcement learning from human feedback (RLHF). In this work, we identify a new vulnerability: while VLM pretraining and instruction tuning generalize well to split-image inputs, safety alignment is typically performed only on holistic images and does not account for harmful semantics distributed across multiple image fragments. Consequently, VLMs often fail to detect and reject harmful split-image inputs, in which unsafe cues emerge only upon combining images. We introduce novel split-image visual jailbreak attacks (\textbf{SIVA}) that exploit this misalignment. Unlike prior optimization-based attacks, which exhibit poor black-box transferability due to architectural and prior mismatches across models, our attacks evolve in progressive phases from naive splitting to an adaptive white-box attack, culminating in a black-box transfer attack. Our strongest strategy leverages a novel adversarial knowledge distillation \textbf{(Adv-KD)} algorithm to substantially improve cross-model transferability. Evaluations on four state-of-the-art modern VLMs and three jailbreak datasets demonstrate that our strongest attack achieves up to 44% higher transfer success than existing baselines. Lastly, we propose efficient ways to address this critical vulnerability in the current VLM safety alignment.
Vision-language models (VLMs) are increasingly deployed on infrared (IR) remote sensing imagery in security-critical settings, yet their adversarial robustness remains unexamined. We present AirflowAttack, to our knowledge the first adversarial attack for IR remote-sensing VLMs and the first to weaponize thermal-airflow turbulence as the perturbation prior. A lightweight generator synthesizes a single input-agnostic perturbation regularized toward physically plausible airflow patterns. Optimized on one surrogate CLIP model, it attains a mean zero-shot scene-classification attack success rate (ASR, the fraction of samples whose top-1 class changes) of 48.5% across five diverse CLIP backbones, far exceeding four IR-specific physical baselines (27.7--37.0%). Applied to six state-of-the-art VLMs, it cuts scene-classification accuracy by up to 38.2% relative, yet paradoxically makes some models more confident in their IR analysis, confabulating the perturbation as genuine thermal evidence such as temperature gradients and convection. Ablations show the airflow prior raises physical plausibility at no measurable cost to attack success. Together with a benchmark spanning eleven models and four tasks, these findings expose critical vulnerabilities in the rapidly expanding IR VLM ecosystem.