ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

~ similar to 2603.20108v1· 20 results

cs.CRcs.AIstat.MLRecentJun 4, 2026

TinyML-Driven Cybersecurity for Autonomous Spacecraft: Latency-Accuracy Analysis for SPARTA RF and Cyber Threat Detection

Van Le, Trevor Tran, Tan Le

This paper analyzes the latency-accuracy trade-offs of various TinyML models for detecting diverse cyber-RF threats on autonomous spacecraft, finding that Logistic Regression offers an effective, low-…

View →
cs.CRcs.AIcs.LGMay 21, 2026

TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting

Quang Duc Nguyen, Siyuan Liang, Yiming Li, Fushuo Huo +1 more

The paper proposes TimeGuard, a novel channel-wise pool training defense, to significantly improve the robustness of time series forecasting against backdoor attacks by addressing signal dilution and…

View →
cs.CReess.SYApr 14, 2026

Threat Modeling and Attack Surface Analysis of IoT-Enabled Controlled Environment Agriculture Systems

Andrii Vakhnovskyi

This paper provides the first comprehensive threat model for IoT-enabled Controlled Environment Agriculture (CEA) systems, identifying 123 unique threats and proposing a defense-in-depth framework to…

View →
cs.CRcs.AIApr 21, 2026

Cyber Defense Benchmark: Agentic Threat Hunting Evaluation for LLMs in SecOps

Alankrit Chona, Igor Kozlov, Ambuj Kumar

The paper introduces a challenging benchmark for LLM agents to perform unsupervised threat hunting on raw Windows event logs, finding that current frontier models perform poorly and are not ready for…

View →
cs.LGcs.CRApr 13, 2026

INTARG: Informed Real-Time Adversarial Attack Generation for Time-Series Regression

Gamze Kirman Tokgoz, Onat Gungor, Tajana Rosing, Baris Aksanli

The paper proposes INTARG, an informed and selective adversarial attack framework for time-series forecasting that significantly increases prediction error by targeting only the most vulnerable time s…

View →
cs.CRcs.AIApr 22, 2026

Mythos and the Unverified Cage: Z3-Based Pre-Deployment Verification for Frontier-Model Sandbox Infrastructure

Dominik Blain

The paper introduces COBALT, a Z3 SMT-based formal verification engine, to proactively detect arithmetic vulnerabilities (CWE-190/191/195) in the critical infrastructure surrounding frontier AI models…

View →
cs.CRApr 17, 2026

Modeling Sparse and Bursty Vulnerability Sightings: Forecasting Under Data Constraints

Cedric Bonhomme, Alexandre Dulaunoy

The paper investigates forecasting sparse and bursty vulnerability sightings, concluding that traditional time-series models like SARIMAX are inadequate, and count-based methods like Poisson regressio…

View →
cs.CRcs.AIMar 25, 2026

Policy-Guided Threat Hunting: An LLM enabled Framework with Splunk SOC Triage

Rishikesh Sahay, Bell Eapen, Weizhi Meng, Md Rasel Al Mamun +4 more

The paper proposes an automated, LLM-enabled threat hunting framework integrated with Splunk to help SOC analysts autonomously monitor evolving threats and prioritize suspicious network traffic.

View →
cs.CRcs.AIRecentMay 22, 2026

Are Frontier LLMs Ready for Cybersecurity? Evidence for Vertical Foundation Models from Dual-Mode Vulnerability Benchmarks

Vivek Dahiya, Sunny Nehra, Vipul Dholariya, Bhavik Shangari +1 more

The paper evaluates frontier LLMs on cybersecurity tasks using dual-mode benchmarks and concludes that general-purpose models are insufficient, advocating for specialized, vertical foundation models.

View →
cs.CRcs.AIRecentMay 28, 2026

How Reliable Are AI Attackers Against a Fixed Vulnerable Target? A 400-Run Empirical Study of LLM Penetration Testing Consistency

Galip Tolga Erdem

This study empirically measures the consistency and success rate of autonomous LLM penetration testing across multiple services, finding statistically significant differences in exploitation capabilit…

View →
cs.CRcs.AIRecentMay 28, 2026

How Reliable Are AI Attackers Against a Fixed Vulnerable Target? A 400-Run Empirical Study of LLM Penetration Testing Consistency

Galip Tolga Erdem

This study empirically measures the consistency and effectiveness of autonomous LLM penetration testing across multiple services, finding statistically significant differences in exploitation rates am…

View →
cs.CRcs.CVMar 18, 2026

Toward Reliable, Safe, and Secure LLMs for Scientific Applications

Saket Sanjeev Chaturvedi, Joshua Bergerson, Tanwi Mallick

This paper addresses the critical need for trustworthy LLMs in science by proposing a comprehensive, multi-layered defense framework and methodology to evaluate unique scientific vulnerabilities.

View →
cs.CRcs.AIcs.CLMar 21, 2026

T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search

Hyomin Lee, Sangwoo Park, Yumin Choi, Sohyun An +2 more

The paper introduces T-MAP, a trajectory-aware evolutionary search method, to discover and generate multi-step adversarial prompts that exploit vulnerabilities in autonomous LLM agents through tool ex…

View →
cs.CRcs.AIcs.LGApr 1, 2026

Safety, Security, and Cognitive Risks in World Models

Manoj Parmar

This paper surveys the risks associated with world models, proposing a unified threat model and demonstrating adversarial attacks that show world models require rigorous safety standards comparable to…

View →
cs.CRcs.AIEmpiricalRecentJun 11, 2026

The Emergence of Autonomous Penetration Capabilities in Large Language Model-Powered AI Systems

Jiaqi Luo, Jiarun Dai, Zhile Chen, Jia Xu +7 more

The authors evaluate the autonomous penetration capabilities of 19 LLMs in a realistic cyberattack scenario.

View →
cs.CRcs.AIcs.CLApr 4, 2026

Safety, Security, and Cognitive Risks in State-Space Models: A Systematic Threat Analysis with Spectral, Stateful, and Capacity Attacks

Manoj Parmar

This paper provides the first systematic threat analysis of State-Space Models (SSMs) in safety-critical applications, introducing novel attack classes and formal metrics to quantify their security an…

View →
cs.CRcs.AIEmpiricalRecentJun 22, 2026

Detecting Malicious Agent Skills in the Wild using Attention

Bacem Etteib, Daniele Lunghi, Tégawendé F. Bissyandé

Developed a detector for identifying malicious skills in a marketplace using a two-stage approach

View →
cs.CRApr 4, 2026

Systematic Integration of Digital Twins and Constrained LLMs for Interpretable Cyber-Physical Anomaly Detection

Konstantinos E. Kampourakis, Vasileios Gkioulos, Sokratis Katsikas

The paper proposes a Digital Twin (DT)-driven hybrid system that combines deterministic heuristics and constrained Large Language Model (LLM) reasoning to achieve highly accurate and interpretable rea…

View →
cs.CRcs.AIcs.CLMay 21, 2026

Blind Spots in the Guard: How Domain-Camouflaged Injection Attacks Evade Detection in Multi-Agent LLM Systems

Aaditya Pai

The paper identifies a critical vulnerability, the Camouflage Detection Gap (CDG), where standard LLM injection detectors fail dramatically when malicious payloads mimic the target domain's language a…

View →