KAN-Robust-Bench: A Benchmark for Evaluating the Robustness of Kolmogorov-Arnold Networks

While machine learning models have demonstrated strong performance in many domains, these models have shown profound vulnerabilities when they are exposed to adversarial threats. While adversarial attacks fall into various categories, the most prominent category in research studies is evasion. In evasion attacks, the adversary generates perturbed versions of samples, which might not be observable by human eyes. These samples generally fool the machine learning models with high confidence. This phenomenon poses a significant security violation against machine learning models. In this paper, we investigate the certified and empirical robustness of various Kolmogorov-Arnold network architectures against strong evasion attacks. At first, we provide the mathematical foundations for randomized smoothing and interval bound propagation, and report the $\ell_2$-certified robustness of the models under randomized smoothing. After that, we systematically evaluate the robustness of various defended and undefended KAN models under FGSM, PGD, and C&W attacks in order to find out the optimal defense strategies and architectures.

Breaking the weakest link to evade vision language models

Vision Language Models (VLMs) have recently emerged as a critical component of multimodal AI systems, enabling joint reasoning over visual and textual inputs in real-world and safety-critical applications. Despite their growing deployment, the robustness of VLMs against adversarial threats remains insufficiently explored, particularly in the context of evasion attacks targeting multimodal alignment. In this work, we investigate the vulnerability of VLMs to adversarial perturbations applied to visual inputs and study two attack settings: untargeted attacks, where the goal is to disrupt the model's interpretation of the original image, and targeted attacks, where the adversary aims to force the model to generate a specific semantic description unrelated to the original image. To efficiently generate adversarial examples, we propose a gradient-based attack method that performs optimization exclusively on the vision encoder of the VLM rather than on the entire multimodal architecture. This design significantly reduces the computational cost and resource requirements of the attack while maintaining strong effectiveness. We evaluate our approach on several open-source VLMs, including Qwen2.5-VL, Granite-Vision, FastVLM, and Phi-3.5-Vision, and show that small, human-imperceptible perturbations can substantially alter the textual interpretation produced by the models. Our findings highlight the vulnerability of modern VLMs to adversarial manipulation and emphasize the need for improved robustness and security mechanisms in multimodal AI systems.

DiffAttack: Evasion Attacks Against Face Recognition via Latent Diffusion Models

Facial biometric identification relies on the distinctiveness of user attributes within a high-dimensional embedding space. However, the decision boundaries of deep face recognition (FR) systems are often sufficiently narrow that they can be conflated, rendering the models vulnerable to adversarial attacks. In such scenarios, the FR system fails to distinguish between an authentic source and a meticulously crafted adversarial face. Existing adversarial methods targeting facial biometrics are limited in both performance and their ability to generate high-quality images that are imperceptible to humans. Moreover, these methods often fail when the source and target images belong to different demographic groups or genders. To address these limitations, we present a novel approach for adversarial face generation via latent-space optimization. We leverage latent diffusion models directly to guide generation toward target identity embeddings, as measured by a face recognition model. Our proposed \textbf{DiffAttack} framework has been evaluated on standard benchmarks, such as the FFHQ and CelebA-HQ datasets. DiffAttack significantly outperforms existing adversarial techniques, achieving a high average attack success rate of 84.86% across multiple face recognition models (e.g., FaceNet). Notably, DiffAttack demonstrates superior transferability, surpassing traditional noise-based methods by over 15.28% and semantic-based approaches by approximately 5.21% on benchmark datasets like FFHQ and CelebA-HQ.

Signal-based Model Access Risk Analysis for AI System Operations Security

Artificial intelligence (AI) systems are now ubiquitous across domains such as security, finance, healthcare, consumer technology, and large-scale cloud services, where they process massive volumes of data and make consequential decisions daily. This widespread adoption has created a broad attack surface through which adversaries can manipulate, evade, extract information from, or otherwise subvert deployed models. Depending on system design and exposure, attackers may have very different forms of access: some observe only final decisions, while others receive confidence scores, intermediate representations, or even full model parameters. While previous surveys typically organize evasion attacks into white-box, gray-box, and black-box categories based on the attacker's knowledge of model internals (architecture, parameters, gradients), this taxonomy often conflates different deployment scenarios that provide vastly different output signals, all labeled as ``black-box'' despite enabling fundamentally different attack strategies. Understanding how evasion attack strategies adapt to the specific information signals returned by deployed systems is critical for organizations making procurement and deployment decisions. To address this gap, we introduce the Signal-based Model Access Risk Taxonomy (SMART), a deployment-oriented framework that classifies attacker access according to the nature and richness of the information signals available from deployed AI systems. Using this taxonomy, we provide a structured overview of evasion attacks across progressively richer levels of information exposure, highlighting how deployment interfaces influence attack capabilities and informing more secure AI deployment and procurement decisions.

UTS at ELOQUENT 2026 Voight-Kampff: structural shifts in AI writing bypass state-of-the-art detectors

We investigate which language model evasion attacks survive state-of-the-art adversarial fine-tuning, developing strategies that sweep the top 5 positions on the ELOQUENT 2026 Voight-Kampff leaderboard. While adversarial fine-tuning trivially closes the 2025 winning evasion recipes, we uncover a fundamental asymmetry in detector vulnerability: pushing generated text out of the detector's training distribution reliably defeats adversarial detection, whereas pulling it into the distribution (e.g., mimicking human training data) fails completely. Exploiting this, we introduce two novel out-of-distribution attack families - cross-decade register attacks and modernist stream-of-consciousness form. Both strategies easily bypass adversarial closure, achieving up to approximately 50x higher fool rates than previous methods while preserving naturalness. Furthermore, experiments show that the obvious deployer countermeasure (augmenting training data with period prose) fails to close the vulnerability. Our findings show that the tested detector families, including adversarially fine-tuned ones, exhibit persistent vulnerabilities under structural out-of-distribution shifts, a mechanism that directly powers our leading competition performance.

Inherited Circuits, Learned Semantics: How Fine-Tuning Creates Evasion Vulnerabilities Invisible to Standard Evaluation

LLMs fine-tuned for security classification are usually evaluated on held-out examples from the same distribution as their training data. We show that this can miss vulnerabilities introduced by fine-tuning itself: models can learn token-level indicator semantics that preserve canonical accuracy while failing under behavior-preserving transformations such as PowerShell alias substitution, command reconstruction, string construction, execution indirection, and case mutation. We study Foundation-Sec-8B-Instruct and its base model, Llama-3.1-8B-Instruct, on matched PowerShell classification cohorts. Causal interventions localize the classification circuit to a late-attention route inherited from Llama rather than created by fine-tuning. Fine-tuning concentrates and semantically specializes this inherited structure, improving baseline behavior while creating transformation-sensitive attack surfaces. A three-tier evasion benchmark finds Foundation-Sec misses on iwr substitution, Invoke-Expression reconstruction, and case-mutated Invoke-Expression/IEX variants that Llama does not share. We also derive a pre-deployment monitoring method: a linear probe at the classification boundary and an indicator-token sign test identify command families where canonical indicators change role after fine-tuning. These signals prioritize red-team variant generation using only canonical inputs, showing that security fine-tuning can improve task accuracy while expanding the evasion surface. These results caution against treating small task-specific fine-tunes as straightforwardly safer security classifiers: specialization can convert inherited model structure into brittle indicator rules that preserve held-out accuracy while expanding the evasion surface. Robust AI-enabled security will require specifying the full transformation space of the task and monitoring semantic drift through fine-tuning.

Benchmarking Autonomous Agents against Temporal, Spatial, and Semantic Evasions

As autonomous agents (e.g., OpenClaw) increasingly operate with deep system-level privileges to execute complex tasks, they introduce severe, unmitigated security risks. Current vulnerability analyses overwhelmingly focus on single-turn, stateless behaviors, overlooking the expanded attack surface inherent in stateful, multi-turn interactions and dynamic tool invocations. In this paper, we propose a novel, multi-dimensional evasion framework targeting LLM-based agent systems. We introduce three stealthy attack vectors: (1) Temporal evasion, which fragments malicious payloads across sequential interaction turns; (2) Spatial evasion, which conceals payloads within complex external artifacts that evade standard LLM parsing mechanisms; and (3) Semantic evasion, which obscures malicious intents beneath benign contextual noise. To systematically quantify these threats, we construct A3S-Bench, a comprehensive benchmark comprising 2,254 real-world agent execution trajectories. Evaluating a standard agent framework separately integrated with 10 mainstream LLM backbones against 20 practical threat scenarios, we demonstrate that our evasion framework elevates the average risk trigger rate from a 28.3\% baseline to 52.6\%. These findings reveal systemic, architecture-level vulnerabilities in current autonomous agent systems that existing defenses fail to address, highlighting an urgent need for defense mechanisms tailored to the unique threats.