Ravshan R

Non stop research.

[zhiniang peng @edwardzpeng]

Sharing my for keynote talk for Offbyone security conference #OB12026 : <A year of hacking with LLMs>

https://t.co/W7NFSnAvij

[Ravshan R @arzedlab]

@edwardzpeng I like ur takes on AI and cybersecurity, and I also think it will make things tougher for entry level jobs, since junior level work is now fully replaceable by AI, and training AI can be cheaper than hiring and training interns

[Ravshan R @arzedlab]

@xvonfers what is the main reason?

[Ravshan R @arzedlab]

Twitter is fresh air after ai shit slop posts from LinkedIn.

[Ravshan R @arzedlab]

@S1r1u5_ I was expecting more of the technical side, like building a harness at least or MCP server, tool communication, and handling failures

I expected cases where AI gets stuck, how do you collect, filter, and organize context to get it unstuck? ;)

[Ravshan R @arzedlab]

@XenoKovah Great idea! I also thinking about it

[Ravshan R @arzedlab]

@S1r1u5_ As I know, Hacktone uses Opus, Codex, or another frontier model.
Suppose a client requests a white-box and provides you with the source code, but at the same time doesn't allow the use of any third-party LLMs due to privacy concerns, what your company do in this situation?

[Ravshan R @arzedlab]

@james406 I don't live in USA, but sheep farm in the Montana is real, I think everyone who is in the tech has similar dreams)

[secret club @the_secret_club]

Striga: Lifting x86 to LLVM IR with Python by @mrexodia

https://t.co/7iYajj8gIZ

[Alex Moshkov @amoshkov]

It’s been quite a while after we wrapped up #PHtalks in Kuala Lumpur 🇲🇾 Time to say a few words:

Damn amazing everything went over there! Thank you, community ❤️

[Positive Technologies Global @PTsecurity_EN]

Great to have @arzedlab at #PHTalks Kuala Lumpur with Kernel Wars: Anti-Cheat Reversing, BYOVD Exploitation and Mitigations. An insightful session on kernel-level tradecraft, anti-cheat internals, and what defenders can realistically rely on.

[Eduardo Vela @sirdarckcat]

... building the future of Vulnerability Research!

Captain Obvious here: vulnerability research isn't gonna look the same in 5 years than how it looked 5 years ago.

We are in the middle of a transition that is helping us scale vulnerability research in new ways!

2/🧵

[Positive Technologies Global @PTsecurity_EN]

Anti-cheats live in the kernel. So do we. Kernel Wars covers anti-cheat reversing, BYOVD abuse, and what actually helps against it. Hear @arzedlab at #PHTalks Kuala Lumpur 🇲🇾: https://t.co/4UZX2BQXI0

[Ravshan R @arzedlab]

@justbyte_ OpenClaw

[Ravshan R @arzedlab]

@eternalsakura13 @offensive_con Waiting a talk, some fresh air after AI bug hunters

[Security BSides Prague @bsidesprg]

🚨 Speaker Announcement – #BSidesPrague2026

🎤 Ravshan Rikhsiev
Adventures in Router Firmware Through Dynamic Taint Analysis
A deep dive into router firmware vulnerabilities using dynamic taint analysis and advanced VR techniques.

#BSides

[Ravshan R @arzedlab]

@SinSinology Cool! Fuzzing or AI?

[Ravshan R @arzedlab]

@0x_shaq I didn't know Claude used in Firefox production code

[Ravshan R @arzedlab]

@HaifeiLi Probably will be more like "probably there is a zero day but not exploitable"
Folks prompting, but no idea how does AI give results, and most interesting moment, they verify result by asking AI.
I think due to over abstraction, it is hard to find deep bugs with AI.

[Ravshan R @arzedlab]

@xvonfers Probably vibe researching bugs :)