While Local Differential Privacy (LDP) serves as a foundational primitive for distributed data collection, its stringent randomization requirements often lead to severe degradation in data representation utility. This degradation stems from the task-agnostic nature of conventional LDP mechanisms, which perturb all dime...
Youngmok Ha, Viktor Schlegel, Yidan Sun et al.· 0 citations
Delphi Scanner is introduced, a static malware detection system for Windows PE files that balances efficiency with behavioral interpretation that uses a convolutional neural network to model Windows API sequences to classify PE and a decoupled interpretation layer based on a rule-based layer to categorize APIs into hig...
Bijied Brahimi, Vincent Cohadon, Gabriel Glazman et al.· 0 citations
Large language models are being integrated into malware triage workflows as reasoning components that summarize static evidence and produce analyst-facing verdicts. This paper shows that the same reasoning capability introduces a new attack surface. We present ALIBI, a semantic cover story attack against frontier LLM-b...
H. Choi, Wonyoung Jung, Haehoon Seo et al.· 0 citations
Federated learning enables collaborative training without sharing patient-level data, but most studies remain simulations. Based on five requirements derived from the literature, we analyzed 14 FL frameworks and found that none fully satisfied these requirements. We present FL-Net, a novel federated clinical research f...
Simon Süwer, Juliane Klemm, E. Acitelli et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Croissant is the de facto machine-readable descriptor for ML datasets: JSON-LD over schema.org. Since version 1.1 it also carries data use conditions, recommending DUO and ODRL for them. What no version specifies is how any of them is evaluated: no decision procedure, no bound on evaluation cost, no outcome for a condi...
Security protocols verification relies on formal tools such as ProVerif and OFMC. This study evaluates whether large language models (LLMs) can perform comparable analysis. We test GPT and DeepSeek in chat and reasoning modes over three runs on 130 obfuscated AnB/AnBx protocols covering 388 security goals, scored again...
Paolo Modesti, Syed Ahmed, Ioannis Sfyrakis et al.· 0 citations
Self-hosted AI agents maintain persistent memory, instructions, and configuration that influence their future behavior. If an agent is compromised, an attacker can exploit the agent's legitimate write permissions to corrupt this self-state, making malicious and benign updates difficult to distinguish at the operating s...
Yimeng Chen, Nathana\"el Denis, Roberto Di Pietro et al.· 0 citations
Metadata Augmented Private Language Evolution (MAPLE) extracts DP tabular metadata and uses in-context learning to firmly ground the initial synthetic distribution in the target domain, and yields a strictly better privacy-utility trade-off.
Eli Chien, Yuzheng Hu, Ryan McKenna et al.· arXiv.org· 2 citations
This work adapts NL2KQL for SLMs with lightweight retrieval and introduces error-aware prompting that targets common parser failures with a handful of mined tips, at a fraction of the tokens KQL's full rule set would require.
Saleha Muzammil, R. Reddy, Vishal Kamalakrishnan et al.· 3 citations
MAS-Shield is proposed, a secure and efficient defense framework designed with a coarse-to-fine filtering pipeline that achieves a 92.5\% recovery rate against diverse adversarial scenarios and reduces defense latency by over 70\% compared to existing methods.
Kai-Xiang Wang, Zhaojiacheng Zhou, Bunyod Suvonov et al.· 2 citations
We introduce the first watermark tailored for diffusion language models (DLMs), an emergent LLM paradigm able to generate tokens in arbitrary order, in contrast to standard autoregressive language models (ARLMs) which generate tokens sequentially. While there has been much work in ARLM watermarking, a key challenge whe...
Thibaud Gloaguen, Robin Staab, Nikola Jovanovi\'c et al.· 0 citations
This paper presents AIREP, a vendor- and model-independent protocol for per-decision AI runtime evidence, a structured reconciler that preserves failure, missing evidence, unevaluated prerequisites, and indeterminate outcomes as distinct states.
