all InfoSec news
Is Watermarking LLM-Generated Code Robust?
March 28, 2024, 4:10 a.m. | Tarun Suresh, Shubham Ugare, Gagandeep Singh, Sasa Misailovic
cs.CR updates on arXiv.org arxiv.org
Abstract: We present the first study of the robustness of existing watermarking techniques on Python code generated by large language models. Although existing works showed that watermarking can be robust for natural language, we show that it is easy to remove these watermarks on code by semantic-preserving transformations.
arxiv can code cs.cr cs.lg easy generated language language models large llm natural natural language python remove robustness semantic study techniques watermarking watermarks
More from arxiv.org / cs.CR updates on arXiv.org
IDEA: Invariant Defense for Graph Adversarial Robustness
2 days, 7 hours ago |
arxiv.org
FairCMS: Cloud Media Sharing with Fair Copyright Protection
2 days, 7 hours ago |
arxiv.org
Efficient unitary designs and pseudorandom unitaries from permutations
2 days, 7 hours ago |
arxiv.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Security Officer Hospital Laguna Beach
@ Allied Universal | Laguna Beach, CA, United States
Sr. Cloud DevSecOps Engineer
@ Oracle | NOIDA, UTTAR PRADESH, India
Cloud Operations Security Engineer
@ Elekta | Crawley - Cornerstone
Cybersecurity – Senior Information System Security Manager (ISSM)
@ Boeing | USA - Seal Beach, CA
Engineering -- Tech Risk -- Security Architecture -- VP -- Dallas
@ Goldman Sachs | Dallas, Texas, United States