Neil Gong retweetledi
Nominations for the AsiaCCS '27 PC have opened. Please share widely, and nominate others or yourselves here: docs.google.com/forms/d/e/1FAI…
English
Neil Gong
161 posts
Neil Gong
@NeilGong
Security, trustworthy AI. Associate Professor, Duke University
Katılım Haziran 2011
244 Takip Edilen1.4K Takipçiler
I’d like to take this opportunity to highlight their work and share a brief summary of our research on federated learning security over the past several years (2018–2025). Many thanks to my amazing former and current students and collaborators—all credit goes to them!
English
Fingerprinting LLMs via Prompt Injection - arxiv.org/pdf/2509.25448
As models proliferate across organizations, questions of provenance–specifically, verifying whether a given model has been derived from a particular released model–become critical.
Establishing provenance is important both for safeguarding intellectual property since training a competitive LLM requires substantial compute, data, and engineering effort, and for ensuring accountability by detecting unauthorized redistribution.
However, reliably establishing provenance is far from trivial, especially once models have been altered through post-processing such as post-training or quantization.
Authors: Yuepeng Hu, Zhengyuan Jiang, Mengyuan Li, Osama Ahmed, Zhicong Huang, Cheng Hong, @NeilGong - @DukeU, @AntGroup
#AISecurity #LLMFingerprinting #PromptInjection #Provenance #ModelOwnership #GenAI #AdversarialML #TrustworthyAI #ModelSafety #CyberSecurity #AIResearch #DataIntegrity #DukeU #AntGroup
English
Our paper "DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks" (arxiv.org/abs/2504.11358) received a Distinguished Paper Award at @IEEESSP! Huge thanks and congratulations to my amazing co-authors Yupei Liu, Yuqi Jia, Jinyuan Jia, and @dawnsongtweets!
English
Deeply humbled and honored to be elected to the American Academy of Arts and Sciences @americanacad! Excited to contribute to the Academy’s mission and advancing the common good!
amacad.org/new-members-20…
American Academy of Arts & Sciences@americanacad
New! Academy member announcement. Dedicated to honoring excellence and advancing the common good, from 1780 to today. amacad.org/news/new-membe…
English
Such an excellent line-up of speakers! Please attend SAGAI @IEEESSP
earlence@EarlenceF
Our @IEEESSP SAGAI workshop on systems-oriented security for AI agents has speaker details (abs/bio) on the website now: sites.google.com/ucsd.edu/sagai… We look forward to seeing you in San Francisco on May 15! As a reminder, we are running this "Dagstuhl" style - real discussions.
English
Our study (arxiv.org/abs/2408.07291) demonstrates that LLMs excel at such information extraction. This highlights the potential for LLMs to automate cyberattacks at scale, posing significant security challenges.
English
Still using symbol replacement, image conversion, and similar strategies (shown below) to protect your email addresses from automated scraping? Our research shows they offer limited effectiveness against LLM-based extraction while making it harder for regular users to email you.
English
Neil Gong retweetledi
The 8th Deep Learning Security and Privacy workshop co-located with IEEE S&P @IEEESSP May 15, 2025, San Francisco (dlsp2025.ieee-security.org) is calling for papers, posters and talks! The workshop seeks your awesome contributions on all aspects of deep learning and security, aiming to bring complementary views together by (a) investigating the security and privacy of deep learning, such as the recent generative models, and (b) exploring the application of deep learning for security and privacy.
We are calling for both proceeding papers (up to 6 pages) and non-archival extended abstracts (up to 3 pages). We will have one best paper award for the accepted papers and one best extended abstract for the accepted non-archival extended abstracts. For the first time, in addition to the talks, we will encourage the authors of the accepted papers to also present the posters for more in-depth discussions!
English
Neil Gong retweetledi
We @OSUbigdata and @osunlp are very excited to host Neil Gong @NeilGong tmr (10:30AM-11:30AM ET, Dec 6th) to give an invited talk on Safe and Robust Generative AI. He will cover several critical safety and robustness issues in generative AI, including preventing the generation of harmful content, detecting AI-generated content through watermarks, and addressing prompt injection in large language models. The talk is open to people outside OSU. DM me for a zoom link, if interested!
English
Neil Gong retweetledi
Excited that our paper on audio watermark benchmarking is accepted to @NeurIPSConf! Congrats to all my amazing collaborators @hbliuustc, Mo Yang, Zheng Yuan, and @NeilGong.
Audio authenticity has become a real issue now and we will keep working on this topic. Stay tuned :)
Lun Wang@lunwang1996
AudioMarkBench: Benchmarking Robustness of Audio Watermarking [arxiv.org/pdf/2406.06979] Despite rapid progress in #audiodeepfake, I feel the related safety risks are still underestimated. Imagine getting a call from somebody you trust who's actually a scammer-controlled bot – this is already happening when a scammer used voice-cloning tech to impersonate President Biden in a series of illegal robocalls during a New Hampshire primary election🚨. Audio watermarking is a powerful tool against misuse of synthetic audio, but our research with @NeilGong's group reveals - Vulnerabilities to even unintentional perturbations. For example, compression/decompression can remove watermarks without impacting audio quality too much. - Uneven robustness across attributes, raising fairness concerns. We still need more robust ways to watermark synthetic audios.
English
I am honored to receive this award, thank you so much @Cylab for this recognition! Looking forward to visiting for the Cylab Partners Conference.
CyLab@CyLab
Prof. @AlinaMOprea, professor in the @KhouryCollege at @Northeastern, has been named @CyLab's 2024 Distinguished Alumni Award recipient. Learn more: cylab.cmu.edu/news/2024/09/0…
English
Glad to see prompt injection is among the interesting competitions. One of the most important security/safety challenges for LLM 😄😄please participate!
Somesh Jha@jhasomesh
Exciting competitions at @satml_conf All of them look super interesting...
English
i'd been low key about my promotions, but whoops, i let the cat out of the bag! many thx to those that supported me along the way! i'd promised my closest collaborators that i'd try my best to be supportive of others just like how the community supported me. (3/3)
English
after putting out a fire, i walk into the theory lunch for new phd students. host was introducing our theory faculty, and i arrived exactly when it was my turn. host said, "elaine, wanna introduce urself?" i looked at the slide absent-mindedly and tried reading thru it (1/3)
English
Was my data used to train an AI model? In our CCS'24 paper (with Zonghao Huang and Michael Reiter), we propose a framework to audit data use in model training, with a formal guarantee on false positive rate (probability of falsely detecting data use) arxiv.org/abs/2407.15100
English