SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces

Reusable skills are becoming a common interface for extending large language model agents, packaging procedural guidance with access to files, tools, memory, and execution environments. However, this modularity introduces attack surfaces that are largely missed by existing safety evaluations: eve...

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...

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...

Still Camouflage, Moving Illusion: View-Induced Trajectory Manipulation in Autonomous Driving

Existing physical adversarial attacks on vision-based autonomous driving induce time-evolving perception errors, including biased object tracking or trajectory prediction, through i sophisticated physical patch inducing detection box drift when entering the view distance, or ii dynamically changi...

Adversarial SQL Injection Generation with LLM-Based Architectures

SQL injection SQLi attacks are still one of the serious attacks ranked in the Open Worldwide Application Security Project OWASP Top 10 threats. Today, with advances in Artificial Intelligence AI, especially in Large Language Models LLMs, an opportunity has been created for automating adversarial...

LLMs for Secure Hardware Design and Related Problems: Opportunities and Challenges

The integration of Large Language Models LLMs into Electronic Design Automation EDA and hardware security is rapidly reshaping the semiconductor industry. While LLMs offer unprecedented capabilities in generating Register Transfer Level RTL code, automating testbenches, and bridging the semantic...

LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments

The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content safety: behavior jailbreak, where an adversary induces an agent to execute dangerous OS-level operations with irreversible consequences. Existing...

When Prompts Become Payloads: A Framework for Mitigating SQL Injection Attacks in Large Language Model-Driven Applications

Natural language interfaces to structured databases are becoming increasingly common, largely due to advances in large language models LLMs that enable users to query data using conversational input rather than formal query languages such as SQL. While this paradigm significantly improves usabili...

Smart Contract Security beyond Detection

Smart contract security has progressed from vulnerability detection toward a broader research agenda that includes semantic reasoning, automated repair, adversarial robustness, and real-time exploit detection. This paper develops a capstone-oriented research narrative around four directions:...

The Art of the Jailbreak: Formulating Jailbreak Attacks for LLM Security beyond Binary Scoring

Jailbreak attacks -- adversarial prompts that bypass LLM alignment through purely linguistic manipulation -- pose a growing operational security threat, yet the field lacks large-scale, reproducible infrastructure for generating, categorizing, and evaluating them systematically. This paper...

Enhancing Adversarial Robustness in Network Intrusion Detection: A Layer-Wise Adaptive Regularization Approach

The new wave of adversarial attacks that utilize gradient-related vulnerabilities in neural network-based classifiers makes Network Intrusion Detection Systems more open to such threats. Although state-of-the-art adversarial training methods have shown promising results in producing more robust...

AI-Driven Security Alert Screening and Alert Fatigue Mitigation in Security Operations Centers: A Comprehensive Survey

Security alert screening is the downstream task of filtering, prioritizing, correlating, and contextualizing alerts for analyst attention in Security Operations Centers. This survey reviews artificial-intelligence-driven alert screening and alert-fatigue mitigation from 2015 to 2026. We synthesiz...

Benchmarking Large Language Models for IoC Recovery under Adversarial Code Obfuscation and Encryption

Software obfuscation and encryption present persistent challenges for program comprehension and security analysis, particularly when adversaries conceal Indicators of Compromise IoCs such as IP addresses within source code. While Large Language Models LLMs have recently demonstrated remarkable...

Information Theoretic Adversarial Training of Large Language Models

Large language models LLMs remain vulnerable to adversarial prompting despite advances in alignment and safety, often exhibiting harmful behaviors under novel attack strategies. While adversarial training can improve robustness, existing approaches are computationally expensive and difficult to...

Automation-Exploit-Legacy

Automation-Exploit Legacy Prototype This repository contain...

The Adversarial Discount - AI, Signal Correlation, and the Cybersecurity Arms Race

We study a contest-theoretic model of adversarial investment in which an attacker and a defender allocate resources to AI-augmented capabilities across multiple attack surfaces. The attacker's investment operates through two channels: it amplifies offensive potency unconditionally and erodes...

EUVD-2026-26445

In Exim before 4.99.2, when the SPA authentication driver is used with an adversarial SPA resource, there can be an out-of-bounds write that crashes the connection instance, or erroneous data processing that divulges data from uninitialized heap memory...

CVE-2026-40687

In Exim before 4.99.2, when the SPA authentication driver is used with an adversarial SPA resource, there can be an out-of-bounds write that crashes the connection instance, or erroneous data processing that divulges data from uninitialized heap memory...