Both traditional heuristics and some common ML detection methods are ill-suited for consistently evolving DGA tactics observed in Gravity Falls, motivating more context-aware approaches and providing a reproducible benchmark for future evaluation.
Adam Dorian Wong, John D. Hastings· arXiv.org· 0 citations
The Digital Agriculture Sandbox is presented, a secure online platform that enables farmers (with limited technical resources) and researchers to collaborate on analyzing farm data without exposing private information and helps bridge the gap between maintaining farm data privacy and utilizing that data to address crit...
Osama Zafar, Rosemarie Santa González, Alfonso Morales et al.· arXiv.org· 0 citations
Feature selection is critical for network intrusion detection systems (NIDS) operating under high-dimensional, highly imbalanced traffic, as found in operational and defense networks. Traditional filter methods rank features using global statistics computed symmetrically across classes and thus fail to capture the asym...
This work proposes PromptMIA, a membership inference attack tailored to federated prompt-tuning, in which a malicious server introduces adversarially crafted prompts and exploits their updates during collaborative training to determine whether a target data point belongs to a client's private dataset.
Quan Nguyen, Min-Seon Kim, Hoang M. Ngo et al.· arXiv.org· 1 citation
Reach audiences
Advertise in front of researchers, engineers, and readers.
A novel framework for approximating ROC and PR curves using quantiles of the score distribution, which can be computed efficiently under secure aggregation and distributed differential privacy, and provides theoretical guarantees on the approximation quality by bounding the Area Error between the true and estimated cur...
ICER is a black-box framework that addresses the gap in text-to-image models in harmful content generation through two components: an LLM-based rewriter that produces fluent, natural-language adversarial prompts, and in-context experience replay that accumulates successful jailbreaking patterns into a reusable prior.
Zhi-Yi Chin, Pin-Yu Chen, Wei-Chen Chiu et al.· 2 citations
This work repurposes cyber-physical process invariants from runtime detection heuristics into a verifiable admission requirement for federated updates, mined automatically from clean operational data, and shows invariant compliance using zero-knowledge proofs to allow clients to prove batch adherence without revealing...
J. Nijsse, Shuai-Feng Su, Benjamin Oholeguy et al.· 0 citations
As large language models (LLMs) become increasingly widespread, preventing unsafe responses to harmful prompts is essential for their safe deployment. Activation steering offers an approach to improving LLM safety by modifying internal activations during inference without updating model parameters. However, a single pr...
Chen-Xi Wang, Rui-Yang Huang, Li Huang et al.· 0 citations
It is shown that seemingly benign crowdsourced contributions can amplify leakage of other records while remaining difficult to identify through data filtering, demonstrating that seemingly benign crowdsourced contributions can amplify leakage of other records while remaining difficult to identify through data filtering...
RAISE is introduced, which trains policy synthesizers from formal verification in two stages, verified supervised fine-tuning (SFT) followed by a reinforcement learning (RL) stage that learns from verifier signal, and it is found that SFT succeeds largely by letting models express authorization logic they already have.
Ying-Ming Zhou, Adarsh Vatsa, William Eiers· 0 citations
Redwing is proposed, a design principle for robust token-level watermarking that generalizes to TTS models at a speech-quality cost close to that of KGW and shows that retokenization is not merely a source of noise: its transition structure can be exploited as a design principle for robust token-level watermarking.
COGNIT-Guard is presented, coupling a validation-calibrated CPU fast gatekeeper with confidence-gated escalation to an NPU-resident 322M bidirectional direct-decision model (Laya-322M) under an asymmetric false-positive penalty.
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.
