Adversarial Vulnerability under Temporal Concept Drift: A Longitudinal Study of Android Malware Detection

We present a longitudinal, drift-aware evaluation of adversarial robustness across more than a decade of Android applications using static and dynamic feature representations extracted from emulator and real-device executions. The dataset is organized into yearly slices and evaluated under three...

Set Shaping Theory As a Complementary Payload-Shaping Layer for Steganography

This paper studies the use of Set Shaping Theory SST as a reversible payload-shaping layer for least significant bit LSB image steganography. The proposal is not intended to replace existing steganographic methods or to compete with them as a new embedding scheme. Instead, SST is positioned as a...

Backdooring Masked Diffusion Language Models

Masked diffusion language models MDLMs are emerging as a compelling new paradigm for text generation, but their training-time security remains largely unexplored. Existing backdoor attacks on Gaussian diffusion models or autoregressive language models do not directly apply to MDLMs because MDLMs...

EUVD-2026-29552

The Adversarial Robustness Toolbox ART thru 1.20.1 contains an insecure deserialization vulnerability CWE-502 in its Kubeflow component's model loading functionality. When loading model weights from a file e.g., model.pt during robustness evaluation, the code uses torch.load without the...

EUVD-2026-29553

The Adversarial Robustness Toolbox ART thru 1.20.1 contains a command-line argument injection vulnerability in its Kubeflow component robustnessevaluationfgsmpytorch.py. The script uses the unsafe eval function to parse string values provided via the --clipvalues and --inputshape command-line...

CVE-2026-31230

The Adversarial Robustness Toolbox ART thru 1.20.1 contains a command-line argument injection vulnerability in its Kubeflow component robustnessevaluationfgsmpytorch.py. The script uses the unsafe eval function to parse string values provided via the --clipvalues and --inputshape command-line...

CVE-2026-31228

The Adversarial Robustness Toolbox ART thru 1.20.1 contains a remote code execution vulnerability in its Kubeflow component. The robustness evaluation function for PyTorch models uses the unsafe eval function to dynamically evaluate user-supplied strings for the LossFn and Optimizer parameters...

PT-2026-40116

The Adversarial Robustness Toolbox ART thru 1.20.1 contains an insecure deserialization vulnerability CWE-502 in its Kubeflow component's model loading functionality. When loading model weights from a file e.g., model.pt during robustness evaluation, the code uses torch.load without the...

Adversarial Robustness Toolbox 安全漏洞

Adversarial Robustness Toolbox is an open-source machine learning security defense and evaluation tool developed by Trusted-AI. Versions of Adversarial Robustness Toolbox 1.20.1 and earlier contained security vulnerabilities. These vulnerabilities stemmed from the robustnessevaluationfgsmpytorch....

CVE-2026-31229

The Adversarial Robustness Toolbox ART thru 1.20.1 contains an insecure deserialization vulnerability CWE-502 in its Kubeflow component's model loading functionality. When loading model weights from a file e.g., model.pt during robustness evaluation, the code uses torch.load without the...

CVE-2026-31230

The Adversarial Robustness Toolbox ART thru 1.20.1 contains a command-line argument injection vulnerability in its Kubeflow component robustnessevaluationfgsmpytorch.py. The script uses the unsafe eval function to parse string values provided via the --clipvalues and --inputshape command-line...

CVE-2026-31228

The Adversarial Robustness Toolbox ART thru 1.20.1 contains a remote code execution vulnerability in its Kubeflow component. The robustness evaluation function for PyTorch models uses the unsafe eval function to dynamically evaluate user-supplied strings for the LossFn and Optimizer parameters...

CVE-2026-31230

The CVE-2026-31230 vulnerability concerns the Adversarial Robustness Toolbox (ART) up to v1.20.1, specifically in its Kubeflow component (robustness_evaluation_fgsm_pytorch.py). The issue arises from using unsafe eval() to parse string values passed via --clip_values and --input_shape, enabling a...

CVE-2026-31228

The connected documents confirm a vulnerability in the Adversarial Robustness Toolbox (ART) up to version 1.20.1, specifically in its Kubeflow component. The root cause is that the robustness evaluation function for PyTorch models uses Python’s unsafe eval() to dynamically evaluate user-supplied ...

PT-2026-40117

The Adversarial Robustness Toolbox ART thru 1.20.1 contains a command-line argument injection vulnerability in its Kubeflow component robustness evaluation fgsm pytorch.py. The script uses the unsafe eval function to parse string values provided via the --clip values and --input shape command-lin...

CVE-2026-31228

The Adversarial Robustness Toolbox ART thru 1.20.1 contains a remote code execution vulnerability in its Kubeflow component. The robustness evaluation function for PyTorch models uses the unsafe eval function to dynamically evaluate user-supplied strings for the LossFn and Optimizer parameters...

Adversarial Robustness Toolbox 安全漏洞

Adversarial Robustness Toolbox is an open-source machine learning security defense and evaluation tool developed by Trusted-AI. Versions of Adversarial Robustness Toolbox 1.20.1 and earlier contained security vulnerabilities. These vulnerabilities stemmed from the robustness evaluation function i...

Adversarial Robustness Toolbox 安全漏洞

Adversarial Robustness Toolbox is an open-source machine learning security defense and evaluation tool developed by Trusted-AI. Versions of Adversarial Robustness Toolbox 1.20.1 and earlier contained security vulnerabilities. These vulnerabilities stemmed from the model loading function in the...

Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack

Agent benchmarks have become the de facto measure of frontier AI competence, guiding model selection, investment, and deployment. However, reward hacking, where agents maximize a score without performing the intended task, emerges spontaneously in frontier models without overfitting. We argue tha...

CVE-2026-31229

The ART (Adversarial Robustness Toolbox) package up to v1.20.1 contains an insecure deserialization vulnerability in its Kubeflow component’s model loading path. Loading model weights (e.g., model.pt) uses torch.load() without weights_only=True, allowing arbitrary Python object deserialization vi...