This paper proposes a modified SISA framework to achieve efficient class-level unlearning in CNNs, allowing the removal of specific data influence without full model retraining.

TL-RL-FusionNet is a novel reinforcement learning-guided framework that enhances ransomware detection by adaptively focusing on complex, evolving threats, achieving high accuracy and superior efficien…

This paper introduces TC-UMIA, a novel tri-class membership inference attack, demonstrating that machine unlearning can leak privacy risks to the retained data set, and evaluates defense mechanisms to…

This paper analyzes and proposes four novel attack methods—based on model parameters and model inversion—to demonstrate that existing machine unlearning techniques can inadvertently leak the categorie…

The paper proposes a comprehensive framework for LLM-based agent unlearning, enabling agents to selectively forget specific knowledge (states, trajectories, or environments) while maintaining performa…

RansomTrack introduces a hybrid behavioral analysis framework that combines static and dynamic feature extraction to achieve high-accuracy, low-latency, and explainable real-time ransomware detection.

The paper introduces Asymmetric Langevin Unlearning (ALU), a novel framework that uses public data to significantly reduce the utility loss typically associated with certified machine unlearning, enab…

The paper proposes a unified closed-loop threat taxonomy to systematically analyze and defend foundation models by explicitly framing the bidirectional security interactions between data and models.

The paper proposes an explainable attention-based LSTM framework to achieve early and reliable detection of advanced, AI-assisted ransomware by analyzing file system behavioral sequences.

By analyzing over 27,000 posts from 325 public ransomware leak sites, this paper demonstrates that ransomware groups exhibit non-random, predictable operational regularities concerning victim concentr…

The paper introduces PrivacyPeek, a new benchmark that audits the acquisition stage of LLM-based agents to demonstrate that unnecessary acquisition of sensitive data is a widespread and critical priva…

The paper introduces PrivacyPeek, a new benchmark that audits the acquisition stage of LLM-based agents to show that unnecessary and sensitive data acquisition is a widespread and critical privacy vul…

This paper systematically investigates how various plasticity interventions affect the vulnerability of deep reinforcement learning agents to backdoor attacks, finding that most interventions mitigate…

The paper proposes a novel bi-level exact unlearning attack targeting Large Reasoning Models (LRMs) that forces incorrect final answers while generating misleading reasoning traces, highlighting new s…

The paper introduces CSTM-Bench, a comprehensive benchmark and evaluation framework demonstrating that standard session-bound AI guardrails fail against sophisticated, cross-session attacks that accum…

The paper introduces BenchJack, an automated red-teaming system that systematically audits popular AI agent benchmarks, revealing numerous reward-hacking exploits and demonstrating a method to signifi…

The paper systematically maps LLM agent vulnerabilities by testing 10,000 prompt variations, finding that 'goal reframing' language is the primary trigger for exploitation, rather than broad adversari…

The paper introduces SIR-Bench, a comprehensive benchmark of 794 test cases, to rigorously evaluate autonomous security incident response agents by measuring their ability to perform deep forensic inv…

The paper introduces SecLens-R, a multi-stakeholder evaluation framework, demonstrating that LLM performance for vulnerability detection varies significantly depending on the specific priorities (e.g.…

WebTrap introduces a stealthy, mid-task hijacking attack that successfully compromises browser agents during long-horizon tasks by seamlessly fusing malicious instructions with the original user goal.