Autoregressive Images Watermarking through Lexical Biasing: an Approach Resistant to Regeneration Attack

Autoregressive AR image generation models have gained increasing attention for their breakthroughs in synthesis quality, highlighting the need for robust watermarking to prevent misuse. However, existing in-generation watermarking techniques are primarily designed for diffusion models, where...

Enhancing Leakage Attacks on Searchable Symmetric Encryption Using LLM-Based Synthetic Data Generation

Searchable Symmetric Encryption SSE enables efficient search capabilities over encrypted data, allowing users to maintain privacy while utilizing cloud storage. However, SSE schemes are vulnerable to leakage attacks that exploit access patterns, search frequency, and volume information. Existing...

SUSE-SU-2022:2660-1 Security update for java-17-openjdk

This update for java-17-openjdk fixes the following issues: Update to upstream tag jdk-17.0.4+8 July 2022 CPU - CVE-2022-21540: Improve class compilation bsc1201694 - CVE-2022-21541: Enhance MethodHandle invocations bsc1201692 - CVE-2022-34169: Improve Xalan supports bsc1201684 - CVE-2022-21549:...