AID, Automated IPI Detection, a data-driven system that continuously logs unauthorized access and suspicious behaviors on smartphones is presented, demonstrating AID's potential as an evidence-support tool that complements current clinic-based interpretation and safety-planning.
Wei-Si Yang, Shi-Nan Liu, Feng Xiao et al.· Proceedings of the ACM on In...· 2 citations
The Agentic Group Attack System (AGAS), a coordinated shilling framework where a central Coordinator directs a group of role-switching worker agents to adaptively promote a target item across different victim families, consistently surpasses strong baselines in target promotion while better preserving benign recommenda...
Q. Nguyen, Trinh Pham, Viet Huynh et al.· 0 citations
Provenance-based intrusion detection systems (PIDS) frequently report strong performance, but the conclusions drawn from these results can be highly sensitive to benchmarking choices and evaluation protocols. We investigate this dependency by re-evaluating representative PIDS on public datasets that meet our audit, lab...
Lorenzo Guerra, Thomas Chapuis, Guillaume Duc et al.· 0 citations
This work introduces a novel quantitative notion of privacy that is both contextual and specific, and relies on concepts inherent to standard Bayesian decision theory, while departing from them in several important respects.
Cameron Bell, Timothy Johnston, A. Luciano et al.· arXiv.org· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
A cost-effective label-only MIA framework based on transferability and model extraction, which removes the restriction that defines the label-only setting, and characterize how leakage transfer depends on surrogate fidelity.
Abdullah Çaglar Öksüz, Anisa Halimi, Erman Ayday· arXiv.org· 0 citations
The proposed MargNet applies an adaptive marginal selection strategy and trains the neural networks to generate data that conforms to the selected marginals, achieving utility close to the best statistical method while offering an average 7$\times$ speedup over it.
Kai Chen, Chen Gong, Tian-Hao Wang· arXiv.org· 0 citations
This paper presents Maverick, a novel approach to private and verifiable LLM inference based on a protocol for delegating matrix-vector multiplication, a dominant operation in LLMs, and combines this verification primitive with LPN-based pseudorandom masking to provide input privacy.
Ben Merbaum, M. Raeisi, Wenhao Wang et al.· 0 citations
Average treatment effect (ATE) estimation in observational studies is a fundamental statistical tool used frequently in social science, medicine, and other fields. These fields often work with sensitive data where privacy protections are important, so a differentially private mechanism for ATE estimation is highly desi...
Duncan Stewardson, Grayson W. White, Adam Groce· 0 citations
This work introduces t-robustness, a stability score defined for each feature independently of any detection model, comparable across an entire feature space, and demonstrates that t-robust feature spaces sustain detection where the baselines collapse.
J. Michel, Abdul Qadir Khan, Majed Jaber et al.· 0 citations
X-amine509 is presented, a two-stage triage system that uses machine learning to rapidly rank certificates by predicted risk and route only the highest-risk items to full deterministic analysis.
Cameron Keith, Shubh Patel, JD Kilgallin et al.· 0 citations
Fully homomorphic encryption (FHE) enables inference on private data without revealing it to the server, but evaluating an entire input under FHE is expensive. We study \emph{selective homomorphic inference}, where only a sensitive region of interest (ROI) is encrypted, and computations independent of that region are p...
Ali Backour, J. Reyes, Jaime Punyed et al.· 0 citations
Results demonstrate that neuromorphic temporal encoding can provide both accurate cyber-attack detection and improved resilience to data poisoning in cyber-physical systems.
A. Kamoona, Sajad Koushkbaghi, Mahdi Jalili et al.· 0 citations
Research Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agility—and an understanding of the rules. The post Learn the rules: The hacker mindset appeared first on Microsoft Research.
Critical flaws, compromised release channels and agentic AI threats landed within days of each other in mid-October 2026. Why “Black October” may say more about how well we now find weaknesses than about the attacks themselves. The post Black October? The Week AI Changed the Cybersecurity Conversation appeared first on GPT-Lab.
