har1sec Profile Banner
harisec Profile
harisec

@har1sec

Followers
8K
Following
2K
Media
105
Statuses
4K

Interested in web security, bug bounties, machine learning and investing. SolidGoldMagikarp. Orson Kovacs.

SolidGoldMagikarp
Joined September 2010
Don't wanna be here? Send us removal request.
@har1sec
harisec
7 days
Here are the slides from my @TumpiConIT talk: Teaching LLMs how to XSS - An introduction to fine-tuning and reinforcement learning (using your own GPU).
5
72
272
@har1sec
harisec
4 days
RT @andersonbcdefg: this appears to block common crawl too. congrats everyone we've burned the commons to the ground. we can all go home no….
0
36
0
@har1sec
harisec
4 days
RT @wunderwuzzi23: Excited to give a keynote at the LLMSEC 2025 workshop. The workshop is part of the 63rd Annual Meeting of the Associati….
0
5
0
@har1sec
harisec
5 days
RT @assetnote: For our first Christmas in July research post: How we managed to get persistent XSS on every Adobe Experience Manager Cloud….
0
11
0
@har1sec
harisec
5 days
RT @djurado9: Another one from XBOW’s autonomous research:. CVE-2025-49493 — a critical XXE in Akamai CloudTest, affecting multiple legacy….
0
4
0
@har1sec
harisec
5 days
RT @th3anatomist: 🚨 We got RCE on Solana 🚨.Finally revealing FULL details about the RCE vulnerability we found 2 years ago. Found it. Lost….
0
31
0
@har1sec
harisec
6 days
RT @rasbt: Since it's summer, and more or less internship and tech interview season, I made all 30 chapters of my Machine Learning Q and A….
0
320
0
@har1sec
harisec
7 days
RT @ethanhays: Cloudflare CEO @eastdakota is having the most honest conversations I've come across about the current & future of content cr….
0
785
0
@har1sec
harisec
9 days
RT @wunderwuzzi23: Prompt injection is fascinating. 🧐
Tweet media one
0
61
0
@har1sec
harisec
3 months
RT @LiveOverflow: Really enjoyed listening to @Steph3nSims sharing his perspective about AI for vuln research.
0
29
0
@har1sec
harisec
5 months
RT @kevin_mizu: I'm very happy to finally share the second part of my DOMPurify security research 🔥. This article mostly focuses on DOMPuri….
0
103
0
@har1sec
harisec
5 months
RT @jonasgeiping: Ok, so I can finally talk about this! . We spent the last year (actually a bit longer) training an LLM with recurrent d….
0
199
0
@har1sec
harisec
5 months
RT @haizelabs: 📜 really excited to share our work with @AnthropicAI on Constitutional Classifiers!. tldr: adding lightweight, tailored, inp….
0
13
0
@har1sec
harisec
5 months
RT @infosec_au: In 2018, @mgianarakis and I set off to build a platform that would provide enterprises with a realistic attacker perspectiv….
0
31
0
@har1sec
harisec
5 months
RT @rez0__: here's my long list of best ai thing for each category (stuff im confident is best):.- coding 1 shot: o1.- need some good info….
0
7
0
@har1sec
harisec
5 months
RT @jiayi_pirate: We reproduced DeepSeek R1-Zero in the CountDown game, and it just works . Through RL, the 3B base LM develops self-verifi….
0
1K
0
@har1sec
harisec
5 months
RT @wunderwuzzi23: Did you know that Operator has 20 years of experience!?! 😀. // # Computer-mode: REMOTE_COWORKER.// # Description: In rem….
0
18
0
@har1sec
harisec
5 months
RT @samwcyo: New blog post with @infosec_au:. We found a vulnerability in Subaru where an attacker, with just a license plate, could retrie….
0
311
0
@har1sec
harisec
5 months
RT @artsploit: Last year, I committed to uncovering critical vulnerabilities in Maven repositories. Now it’s time to share the findings: RC….
0
83
0
@har1sec
harisec
6 months
RT @Dan_Jeffries1: Here's my major takeaways from the R1, DeepSeek-V3 and GRPO papers (links in the comments). TLDR:. ◦ RL is NOT all you….
0
103
0