The paper analyzes how AI-driven adaptive adversaries exploit implementation-level weaknesses in Public Key Cryptography, suggesting that current algorithm-centric security models are insufficient.

The paper demonstrates that encoding harmful prompts as genuine mathematical problems, rather than just using mathematical formatting, effectively bypasses the safety filters of large language models.

The paper introduces PLM-NIDS, a novel intrusion detection system that models network flows as a language based solely on L3/L4 metadata, successfully detecting attacks by identifying deviations from…

The paper introduces PLM-NIDS, a novel intrusion detection system that models network flows as a language based solely on L3/L4 metadata, successfully detecting attacks by identifying deviations from…

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

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

The paper evaluates prompt injection defenses and finds that only external output filtering, implemented in application code, reliably prevents secret leaks from LLMs, demonstrating that model-based d…

The paper introduces an LLM-driven evolutionary computation framework to automatically optimize prompts, significantly increasing the cracking rate of passwords generated by LLMs from 2.02% to 8.48%.

The paper evaluates AI's effectiveness in detecting network intrusions and cryptographic side-channel leakage, finding high accuracy in stable environments but performance degradation with novel traff…

The paper develops a formal theory to analyze how throughput changes in AI-enhanced cybersecurity pipelines when stage capacities are perturbed by multipliers.

The security of LLM agents is critically dependent on their system prompt configuration, which creates a brittle attack surface that can be exploited by attackers inverting the prompt's core assumptio…

ZERO-APT introduces a novel closed-loop adversarial framework for automated penetration testing that simulates attacks against an intelligent, real-time defending system, achieving a high attack succe…

The paper introduces SeedHijack, a backdoor attack that manipulates the pseudorandom number generation process in LLMs to force specific token selections, and proposes a hardware quantum random number…

The paper benchmarks current frontier computer-using agents against hand-crafted attacks, finding that while they are highly safe in browser tasks, this safety does not generalize to other domains lik…

This paper improves machine learning attacks against the Learning with Errors (LWE) problem by demonstrating that using larger, repeated datasets and a stepwise regression technique allows for the rec…

The paper proposes a black-box attack using a hierarchical genetic algorithm to induce 'overthinking' in Large Reasoning Models, demonstrating that this vulnerability can cause significant resource ex…

The paper proposes using deep learning to empirically test the indistinguishability of various post-quantum and hybrid cryptographic schemes, finding that no tested combination showed a significant ad…

The paper demonstrates that current defenses against malicious fine-tuning of foundation models are insufficient because they only address fixed attacks, and introduces a unified adaptive attack that…

QSignAI is an open-source platform that integrates quantum-randomness-seeded identity signatures into a conversational AI social messaging system, demonstrating a practical bidirectional link between…

This paper provides the first comprehensive review of threats and defenses specifically targeting on-device AI inference, revealing a significant imbalance where certain attack types, like adversarial…