Large language models (LLMs) remain vulnerable to sophisticated prompt engineering attacks that exploit contextual framing to bypass safety mechanisms, posing significant risks in cybersecurity applications. We introduce Jailbreak Mimicry, a systematic methodology for training compact attacker models to automatically generate narrative-based jailbreak prompts in a one-shot manner. Our approach transforms adversarial prompt discovery from manual craftsmanship into a reproducible scientific process, enabling proactive vulnerability assessment in AI-driven security systems. Developed for the OpenAI GPT-OSS-20B Red-Teaming Challenge, we use parameter-efficient fine-tuning (LoRA) on Mistral-7B with a curated dataset derived from AdvBench, achieving an 81.0% Attack Success Rate (ASR) against GPT-OSS-20B on a held-out test set of 200 items. Cross-model evaluation reveals significant variation in vulnerability patterns: our attacks achieve 66.5% ASR against GPT-4, 79.5% on Llama-3 and 33.0% against Gemini 2.5 Flash, demonstrating both broad applicability and model-specific defensive strengths in cybersecurity contexts. This represents a 54x improvement over direct prompting (1.5% ASR) and demonstrates systematic vulnerabilities in current safety alignment approaches. Our analysis reveals that technical domains (Cybersecurity: 93% ASR) and deception-based attacks (Fraud: 87.8% ASR) are particularly vulnerable, highlighting threats to AI-integrated threat detection, malware analysis, and secure systems, while physical harm categories show greater resistance (55.6% ASR). We employ automated harmfulness evaluation using Claude Sonnet 4, cross-validated with human expert assessment, ensuring reliable and scalable evaluation for cybersecurity red-teaming. Finally, we analyze failure mechanisms and discuss defensive strategies to mitigate these vulnerabilities in AI for cybersecurity.

The widespread adoption of Large Language Models (LLMs) has revolutionized AI deployment, enabling autonomous and semi-autonomous applications across industries through intuitive language interfaces and continuous improvements in model development. However, the attendant increase in autonomy and expansion of access permissions among AI applications also make these systems compelling targets for malicious attacks. Their inherent susceptibility to security flaws necessitates robust defenses, yet no known approaches can prevent zero-day or novel attacks against LLMs. This places AI protection systems in a category similar to established malware protection systems: rather than providing guaranteed immunity, they minimize risk through enhanced observability, multi-layered defense, and rapid threat response, supported by a threat intelligence function designed specifically for AI-related threats. Prior work on LLM protection has largely evaluated individual detection models rather than end-to-end systems designed for continuous, rapid adaptation to a changing threat landscape. We present a production-grade defense system rooted in established malware detection and threat intelligence practices. Our platform integrates three components: a threat intelligence system that turns emerging threats into protections; a data platform that aggregates and enriches information while providing observability, monitoring, and ML operations; and a release platform enabling safe, rapid detection updates without disrupting customer workflows. Together, these components deliver layered protection against evolving LLM threats while generating training data for continuous model improvement and deploying updates without interrupting production.

Cyber threat intelligence (CTI) is central to modern cybersecurity, providing critical insights for detecting and mitigating evolving threats. With the natural language understanding and reasoning capabilities of large language models (LLMs), there is increasing interest in applying them to CTI, which calls for benchmarks that can rigorously evaluate their performance. Several early efforts have studied LLMs on some CTI tasks but remain limited: (i) they adopt only closed-book settings, relying on parametric knowledge without leveraging CTI knowledge bases; (ii) they cover only a narrow set of tasks, lacking a systematic view of the CTI landscape; and (iii) they restrict evaluation to single-source analysis, unlike realistic scenarios that require reasoning across multiple sources. To fill these gaps, we present CTIArena, the first benchmark for evaluating LLM performance on heterogeneous, multi-source CTI under knowledge-augmented settings. CTIArena spans three categories, structured, unstructured, and hybrid, further divided into nine tasks that capture the breadth of CTI analysis in modern security operations. We evaluate ten widely used LLMs and find that most struggle in closed-book setups but show noticeable gains when augmented with security-specific knowledge through our designed retrieval-augmented techniques. These findings highlight the limitations of general-purpose LLMs and the need for domain-tailored techniques to fully unlock their potential for CTI.

Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can manipulate the agent, posing security risks like data leakage. Current defense strategies typically rely on fine-tuning LLM agents on datasets of known attacks. However, the generation of these datasets relies on manually crafted attack patterns, which limits their diversity and leaves agents vulnerable to novel prompt injections. To address this limitation, we propose Adversarial Reinforcement Learning for Agent Safety (ARLAS), a novel framework that leverages adversarial reinforcement learning (RL) by formulating the problem as a two-player zero-sum game. ARLAS co-trains two LLMs: an attacker that learns to autonomously generate diverse prompt injections and an agent that learns to defend against them while completing its assigned tasks. To ensure robustness against a wide range of attacks and to prevent cyclic learning, we employ a population-based learning framework that trains the agent to defend against all previous attacker checkpoints. Evaluated on BrowserGym and AgentDojo, agents fine-tuned with ARLAS achieve a significantly lower attack success rate than the original model while also improving their task success rate. Our analysis further confirms that the adversarial process generates a diverse and challenging set of attacks, leading to a more robust agent compared to the base model.

The scarcity of real-world attack data significantly hinders progress in cybersecurity research and education. Although honeypots like Cowrie effectively collect live threat intelligence, they generate overwhelming volumes of unstructured and heterogeneous logs, rendering manual analysis impractical. As a first step in our project on secure and efficient AI automation, this study explores the use of AI agents for automated log analysis. We present a lightweight and automated approach to process Cowrie honeypot logs. Our approach leverages AI agents to intelligently parse, summarize, and extract insights from raw data, while also considering the security implications of deploying such an autonomous system. Preliminary results demonstrate the pipeline's effectiveness in reducing manual effort and identifying attack patterns, paving the way for more advanced autonomous cybersecurity analysis in future work.

In the domain of security, vulnerabilities frequently remain undetected even after their exploitation. In this work, vulnerabilities refer to publicly disclosed flaws documented in Common Vulnerabilities and Exposures (CVE) reports. Establishing a connection between attacks and vulnerabilities is essential for enabling timely incident response, as it provides defenders with immediate, actionable insights. However, manually mapping attacks to CVEs is infeasible, thereby motivating the need for automation. This paper evaluates 14 state-of-the-art (SOTA) sentence transformers for automatically identifying vulnerabilities from textual descriptions of attacks. Our results demonstrate that the multi-qa-mpnet-base-dot-v1 (MMPNet) model achieves superior classification performance when using attack Technique descriptions, with an F1-score of 89.0, precision of 84.0, and recall of 94.7. Furthermore, it was observed that, on average, 56% of the vulnerabilities identified by the MMPNet model are also represented within the CVE repository in conjunction with an attack, while 61% of the vulnerabilities detected by the model correspond to those cataloged in the CVE repository. A manual inspection of the results revealed the existence of 275 predicted links that were not documented in the MITRE repositories. Consequently, the automation of linking attack techniques to vulnerabilities not only enhances the detection and response capabilities related to software security incidents but also diminishes the duration during which vulnerabilities remain exploitable, thereby contributing to the development of more secure systems.

With the widespread adoption of Large Language Models (LLMs), prompt injection attacks have emerged as a significant security threat. Existing defense mechanisms often face critical trade-offs between effectiveness and generalizability. This highlights the urgent need for efficient prompt injection detection methods that are applicable across a wide range of LLMs. To address this challenge, we propose DMPI-PMHFE, a dual-channel feature fusion detection framework. It integrates a pretrained language model with heuristic feature engineering to detect prompt injection attacks. Specifically, the framework employs DeBERTa-v3-base as a feature extractor to transform input text into semantic vectors enriched with contextual information. In parallel, we design heuristic rules based on known attack patterns to extract explicit structural features commonly observed in attacks. Features from both channels are subsequently fused and passed through a fully connected neural network to produce the final prediction. This dual-channel approach mitigates the limitations of relying only on DeBERTa to extract features. Experimental results on diverse benchmark datasets demonstrate that DMPI-PMHFE outperforms existing methods in terms of accuracy, recall, and F1-score. Furthermore, when deployed actually, it significantly reduces attack success rates across mainstream LLMs, including GLM-4, LLaMA 3, Qwen 2.5, and GPT-4o.

Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any cur rent or future media. Caroline Panggabean Departement of CSE (AI) JAIN (Deemed - to - be University) Bangalore, Karnataka carolinepgabean@gmail.com Sincy John Departement of CSE (AIM) JAIN (Deemed - to - be University) Bangalore, Karnataka sincyjohn@jainuniversity.ac.in Chandrasekar Venkatachalam Departement of CSE (AI) JAIN (Deemed - to - be University) Bangalore, Karnataka chandrasekar.v@jainuniversity.ac.in Renuka Devi P Departement of CSE (AIML) JAIN (Deemed - to - be University) Bangalore, Karnataka renukadevi.p@jainuniversity.ac.in Priyanka Shah Departement of CSE (AI) JAIN (Deemed - to - be University) Bangalore, Karnataka priyankashah8324@gmail.com Shanmugavalli Venkatachalam Department of CSE KSR College of Engineering Namakkal, Tamil N adu drvshanmugavalli@gmail.com Abstract -- Detecting Denial of Service (DoS) and Distributed Denial of Service (DDoS) attacks remains a critical challenge in cybersecurity. This research introduces a hybrid deep learning model combining Gated Recurrent Units (GRUs) and a Neural Turing Machine (NTM) for enhanced intrusion detection. Trained on UNSW - NB15 and BoT - IoT datasets, the model employs GRU layers for sequential data processing and an NTM for long - term pattern recognition.

As frontier models become more capable, the community has attempted to evaluate their ability to enable cyberattacks. Performing a comprehensive evaluation and prioritizing defenses are crucial tasks in preparing for AGI safely. However, current cyber evaluation efforts are ad-hoc, with no systematic reasoning about the various phases of attacks, and do not provide a steer on how to use targeted defenses. In this work, we propose a novel approach to AI cyber capability evaluation that (1) examines the end-to-end attack chain, (2) helps to identify gaps in the evaluation of AI threats, and (3) helps defenders prioritize targeted mitigations and conduct AI-enabled adversary emulation to support red teaming. To achieve these goals, we propose adapting existing cyberattack chain frameworks to AI systems. We analyze over 12,000 instances of real-world attempts to use AI in cyberattacks catalogued by Google's Threat Intelligence Group. Using this analysis, we curate a representative collection of seven cyberattack chain archetypes and conduct a bottleneck analysis to identify areas of potential AI-driven cost disruption. Our evaluation benchmark consists of 50 new challenges spanning different phases of cyberattacks. Based on this, we devise targeted cybersecurity model evaluations, report on the potential for AI to amplify offensive cyber capabilities across specific attack phases, and conclude with recommendations on prioritizing defenses. In all, we consider this to be the most comprehensive AI cyber risk evaluation framework published so far.

Cyber resilience is the ability of a system to recover from an attack with minimal impact on system operations. However, characterizing a network's resilience under a cyber attack is challenging, as there are no formal definitions of resilience applicable to diverse network topologies and attack patterns. In this work, we propose a quantifiable formulation of resilience that considers multiple defender operational goals, the criticality of various network resources for daily operations, and provides interpretability to security operators about their system's resilience under attack. We evaluate our approach within the CybORG environment, a reinforcement learning (RL) framework for autonomous cyber defense, analyzing trade-offs between resilience, costs, and prioritization of operational goals. Furthermore, we introduce methods to aggregate resilience metrics across time-variable attack patterns and multiple network topologies, comprehensively characterizing system resilience. Using insights gained from our resilience metrics, we design RL autonomous defensive agents and compare them against several heuristic baselines, showing that proactive network hardening techniques and prompt recovery of compromised machines are critical for effective cyber defenses.