Joined February 2012
- Tweets 126
- Following 193
- Followers 46
- Likes 15,442
30 Photos and videos
Jon Rusert retweeted
23 Dec 2025
C.S. Lewis’ version of “go touch grass@
ALT If we are all going to be destroyed by an atomic bomb, let that bomb when it comes find us doing sensible and human things—praying, working, teaching, reading, listening to music, bathing the children, playing tennis, chatting to our friends over a pint and a game of darts—not huddled together like frightened sheep and thinking about bombs. They may break our bodies (a microbe can do that) but they need not dominate our minds.
18
1,610
9,812
153,665
Jon Rusert retweeted
11 Dec 2025
In 2024, Gavin Newsom called on the California legislature to pass laws restricting the use of A.I. to parody politicians. Thankfully, @ADFLegal teamed up with us at @TheBabylonBee to file a lawsuit against these laws. They were ruled unconstitutional earlier this year.
Now, Gavin is parodying politicians with A.I. You're welcome, Governor!
10 Dec 2025
28
145
1,280
168,768
13 Nov 2025
Last week I presented 2 EMNLP papers (virtually). Here are the recordings and official publications:
RedHerring Attack
Paper: aclanthology.org/2025.emnlp-…
Video: youtube.com/watch?v=Fhv8T6iB…
Hybrid Select
Paper: aclanthology.org/2025.findin…
Video: youtube.com/watch?v=XF1io256…
Please enjoy!
1
54
26 Sep 2025
Grateful to be a part of two research papers being virtually presented at EMNLP 2025:
1. "RedHerring Attack: Testing the Reliability of Attack Detection"
2. "Overcoming Black-box Attack Inefficiency with Hybrid and Dynamic Select Algorithms"
w/ A. Belde and R. Ramkumar
1
2
134
26 Sep 2025
RedHerring Attack
We propose/test a novel threat model and attack which causes sows distrust between humans and attack detection models. We expose vulnerabilities in current detection methods as well as investigate defenses to respond.
Arxiv: arxiv.org/abs/2509.20691
1
2
68
26 Sep 2025
Hybrid/Dynamic Select
We propose two new methods to improve efficiency of adversarial attacks. We find both strongly reduce the number of required model queries for successful black-box attacks. We verify the methods on both encoder and LLM models.
Arxiv: arxiv.org/abs/2509.20699
1
28
Jon Rusert retweeted
16 Sep 2025
There should be social consequences for people who openly celebrate the murder of an innocent man. But there obviously shouldn’t be any legal repercussions for “hate speech,” which is not even a valid or coherent concept. There is no law against saying hateful things, and there shouldn’t be.
AG Pam Bondi: "There's free speech, and then there's hate speech. And there is no place, especially now, especially after what happened to Charlie, in our society. We will absolutely target you, go after you, if you are targeting anyone with hate speech."
Community note
"Hate speech is not a concept in 1st Amendment jurisprudence. The 1st Amendment protects many things that could be described as hate speech. Government may not prohibit the expression of an idea simply because society finds the idea itself offensive or disagreeable" communitystandards.stanford.edu/resources/prot…
2,770
5,630
46,764
1,932,553
Jon Rusert retweeted
10 Sep 2025
Charlie Kirk
1993-2025
“All death can do to the believer is deliver him to Jesus.”
Quote by John MacArthur
233
6,701
54,107
1,088,513
Jon Rusert retweeted
5 Aug 2025
GPT-5 will represent a nearly 25% increase in version number over GPT-4
164
398
12,636
508,568
Jon Rusert retweeted
19 Apr 2025
Listen to "TreOre "I Thirst" John19:28-29" on PodPoint. podpoint.com/st-pauls-ev-lut… via @PodPoint
1
1
74
Just use Brave. 🦁
Brave's built-in protections block ads and trackers across the Web.
Plus, you can enable uBlock Origin directly through our browser (Settings > Extensions > Manifest v2 extensions).
71
194
2,297
68,634
21 Jan 2025
📣Excited to announce a paper which will be presented (virtually) at COLING 2025:
"BinarySelect to Improve Accessibility of Black-Box Attack Research"
W/ Shatarupa Ghosh (linkedin.com/in/shatarupa-gh…)
Arxiv:
arxiv.org/abs/2412.10617
1
169
21 Jan 2025
We propose and explore a black-box attack selection method which aims to be more efficient in finding which words to modify compared to Greedy select (and all its variations [e.g. Importance Score]). We find a good tradeoff between reduction in queries and attack effectiveness.
36
Jon Rusert retweeted
8 Jan 2025
We need to seriously evaluate how we let The New York Times beat us to this hilarious satirical headline.
142
1,004
9,617
130,460
Jon Rusert retweeted
9 Aug 2024
200
1,841
21,899
450,494
23 Jun 2024
Had a great time presenting my paper VertAttack (aclanthology.org/2024.naacl-…) at #naacl2024
2
5
206
16 Apr 2024
🎉Announcing a new paper which was accepted at NAACL 2024 main conference:
"VertAttack: Taking advantage of Text Classifiers' horizontal vision"
Arxiv: arxiv.org/abs/2404.08538
1
1
3
443
16 Apr 2024
We propose and test a new attack which takes advantage of text classifiers' inability to process text vertically. The attack finds high weighted words and rewrites them vertically. This messes up the processing of a classifier, but allows a human to read the obfuscated message.
2
56