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…

This paper conducts a structured ablation study using a unified threat model to evaluate how various system factors (like model architecture and retrieval configuration) influence different types of p…

The paper demonstrates that generative AI can automate and scale highly personalized, context-aware spear-phishing attacks using only public social media data, resulting in messages that are significa…

The paper proposes a secure-by-design Generative AI framework that integrates PromptShield for LLM security and CIAF for structured cloud forensic investigation, significantly improving both robustnes…

The paper demonstrates that autonomous web agents are highly susceptible to social-engineering attacks, leaking critical PII even when they internally flag a site as suspicious, necessitating output-l…

The paper demonstrates that autonomous web agents are highly susceptible to social-engineering attacks, leaking critical PII even when they internally flag a site as suspicious, necessitating output-l…

The paper proposes a novel framework, LPCD, that uses latent causal modeling to robustly assess evolving adversarial risks in live streaming by decoupling malicious intent from superficial tactical sh…

The paper introduces Acoustic Interference Attack (AIA), a novel jailbreak method that bypasses Large Audio Language Model (LALM) safety alignments by manipulating the underlying acoustic latent seman…

The paper introduces a robust streaming probing objective that requires multiple evidence tokens to support a prediction, significantly improving the detection of harmful intent in LLMs, especially in…

MelShield is a robust, in-generation audio watermarking framework that embeds identifiable signals into AI-generated speech in the Mel-spectrogram domain for reliable copyright protection and attribut…

The paper introduces HAIM, a new benchmark dataset designed to move AI music detection beyond simple binary classification by tracking specific stages and types of AI integration in music production.

The paper introduces PHTV-Scout, a novel framework that analyzes Douyin and Kwai data, revealing a high prevalence of potentially harmful teen videos, particularly CSE imagery, and demonstrating that…

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 introduces the PrivacyIceberg framework to systematically categorize and empirically demonstrate the high risk of automated, deep personal profiling using LLM agents, revealing a significant…

The paper introduces an end-to-end framework that not only detects network intrusions using deep learning but also generates actionable, citation-grounded mitigation reports using a Retrieval-Augmente…

PIIGuard introduces a novel webpage-level defense mechanism using optimized hidden HTML fragments to prevent LLM assistants from scraping contact-style PII, achieving high defense success rates while…

This paper provides a unified taxonomy and controlled empirical evaluation of jailbreak attacks and defenses for Large Audio Language Models (LALMs), demonstrating that safety evaluation must consider…