Recent frameworks in differential privacy (DP), such as privacy loss distributions and $f$-DP, provide lossless representations of the privacy leakage of mechanisms. These approaches are often considered to yield tighter $(\varepsilon, \delta)$-DP guarantees than those obtained from relaxed notions such as R\'enyi DP....
Cross-model KV cache sharing reduces prefill computation by allowing a receiver model to reuse prefix KV states generated by a related sender model. Existing methods optimize such reuse for latency and generation quality, but its safety implications remain unclear. In this work, we systematically evaluate this issue ac...
Zhi-Wei Lin, Jia-Hao Liu, Yan Liu et al.· 1 citation
As agentic AI systems take on increasingly complex and consequential tasks, securing them against prompt injection becomes critical. Existing defenses often rely on detecting or reasoning about injected malicious instructions and can therefore remain vulnerable to adaptive attacks that optimize the injection itself. Di...
Michael Cardei, Anjun Hu, Chen-Rui Ma et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
On-device inference reduces exposure to remote infrastructure, but it does not establish privacy for an operating-system assistant that aggregates cross-application data, retains derived state, or delegates actions. We present a feature-boundary audit method for OS-integrated AI. It combines a taxonomy of six privacy-f...
Large language model agents use skills that package reusable instructions, code, and resources. Existing skill-injection attacks exploit trust in these packages by adding malicious content. As agents become more capable, however, they can skip unnecessary steps, inspect code, and reject unrelated actions. We introduce...
Haochang Hao, Dehai Min, Zhifang Zhang et al.· 0 citations
Large language models (LLMs) increasingly rank products, documents, and recommendations for user queries, which makes manipulating these rankings a growing concern for fairness and information integrity. Research on generative engine optimization (GEO) has produced many manipulation methods, but each is evaluated on it...
Ojas Nimase, Zhe Chen, Yue Zhao et al.· 0 citations
Extracting MITRE ATT&CK techniques from cyber threat intelligence (CTI) reports is an open-set, multi-label problem requiring both high recall (not missing techniques) and high precision (not hallucinating unsupported ones). Existing rule-based, supervised, and LLM-based methods struggle to achieve both: rule-based and...
Yutong Cheng, Changze Li, Raihan Sultan Pasha Basuki et al.· 0 citations
Distillation via reasoning traces exposes frontier models to adversarial third parties, who can bypass their guardrails and misappropriate their capabilities. Existing antidistillation defenses perturb the teacher's sampling distribution to hinder downstream student learning, but these perturbations also degrade the tr...
Max Hartman, Vidhata Jayaraman, Moulik Choraria et al.· 0 citations
As agentic computing systems grow increasingly popular, they raise serious security concerns due to their susceptibility to various attacks. While prior research efforts aim to mitigate these concerns, they are often too coarse-grained and offer no formal correctness guarantees. In this work, we present a novel approac...
Nils Palumbo, Sarthak Choudhary, Jihye Choi et al.· 0 citations
This work provides the first systematic investigation into probing model internals across a conversation trajectory, moving beyond static, single-prompt analysis to capture the evolving state of privacy-sensitive interactions, and illustrating their applicability across contexts, attack styles, multiple base models, an...
Prompt-security claims for large language models (LLMs) are often compared as properties of individual attacks or defenses, although measured harmfulness depends on the target model, access setting, attack and defense configuration, prompt sample, and judger. We systematize 272 studies through three linked, multi-label...
Hanbin Hong, Shuang Wu, Shuya Feng 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.
