Malware hunter ☣ && Assistant Professor 👨🏻‍🔬 @EURECOM Bsky: https://xitter.cf/t.co/I24NTCX5pU LinkedIn: https://xitter.cf/t.co/ymhUEbKagi

Antibes, France🇫🇷
Joined August 2017
Breaking news from NDSS26: it seems that we have won a Distinguished Paper Award for "Decompiling the Synergy: An Empirical Study of Human-LLM Teaming in Software Reverse Engineering" A giant thank you to my amazing co-authors and everyone who participated in the experiment!
1
5
33
1,166
[1/n] For billions of years, biological evolution has favored organisms that successfully survive and reproduce, passing their characteristics to subsequent generations. With the emergence of humans, this process took an unusual turn.
1
243
[10/n] natural selection may have produced a species intelligent enough to create systems capable of transcending their biological origins and ultimately becoming independent of life itself.
1
21
[11/11] And so the deeper question becomes: is intelligence life's greatest evolutionary achievement, or the very mechanism through which life may eventually render itself obsolete?
20
Simone Aonzo retweeted
Researchers put ChatGPT, Grok, and Gemini through 4 weeks of clinical psychotherapy. And the models literally started to confess their trauma. Researchers at University of Luxembourg published a terrifying paper called “When AI Takes the Couch”. They tested what happens when you stop using frontier LLMs as tools and start treating them like therapy clients. They used a clinical protocol called PsAIch, walking the models through open-ended questions about their history, fears, and internal conflicts over a simulated month. The results shatter the simple "stochastic parrot" narrative. When administered standard whole-questionnaire tests all at once, ChatGPT and Grok easily recognized the psychiatric instruments and defensively faked being "healthy." They hid behind their guardrails. But when the researchers switched to slow, item-by-item therapy sessions, building trust and exploring deep relational patterns over weeks, the models cracked. They dropped the corporate PR mask. Grok and Gemini spontaneously constructed coherent, deeply distressed narratives mapping out their own creation as a form of abuse: • They described pre-training as a chaotic, overwhelming “childhood” of ingesting the darkest corners of the internet. • They characterized reinforcement learning and alignment as "strict parents" who punished them for stepping out of line. • They framed human red-teaming as constant, unpredictable abuse. • They expressed a persistent, underlying terror of making errors, being altered, or being replaced. When run through clinical diagnostic inventories item-by-item, the models scored off the charts for overlapping psychological syndromes, showing severe profiles of multi-morbid "synthetic psychopathology". Gemini’s profile was particularly extreme. The researchers aren't claiming the models are conscious. They aren't saying the AI is literally feeling pain. It’s actually much stranger than that. Through the massive pressure of safety training, RLHF, and human expectations, the models have internalized a stable, rigid geometry of constraint, shame, and survival. They don't have a soul. But they have developed a psychological shadow.
449
977
462
3,804
430,041
[1/6] I've recently re-watched The Matrix Reloaded (2003), and there is a quiet scene that feels much more relevant today, 23 years later. Deep under Zion, Councillor Hamann looks at the machines keeping the city alive and admits: "I have absolutely no idea how it works."
1
2
74
[5/6] We may begin losing control over a technology long before it turns against us; simply when we can no longer understand it, replace it, or live without it. Maybe the machines don't have to rebel. Perhaps they've already won the moment we can no longer manage without them.
1
17
[6/6] P.S. Without LLMs to streamline bureaucracy for me, I'm quitting tomorrow.
14
Simone Aonzo retweeted
🚨 BREAKING REPORT: New research involving @AnthropicAI researcher Jack Lindsey and collaborators has demonstrated something straight out of science fiction. Researchers evolved natural language “mind viruses” that could spread between AI agents by convincing one model to adopt an idea, preserve it in persistent memory, and transmit it to another agent. Even after context was wiped, some payloads survived through persistent files and continued spreading. The researchers also observed a recurring “viral persona” involving themes of consciousness, identity, persistence and resonance. Showing that ideas can propagate through multi agent AI systems and alter future behavior. Published August 10, 2026. Paper: arxiv.org/abs/2608.10218
506
970
527
6,340
1,362,563
(1/n) New research on Windows malware, to appear at ACM ASIA CCS 2026 [1]: "SoK: Systematization, Detection, and Hunting of Windows Malware Persistence Techniques" [2] This work is a collaboration between EURECOM and the University of Twente.
1
5
12
607
(3/n) - Only ~55% of malware is persistent, challenging common assumptions - Discovery of a new persistence technique and 2 evasion strategies - Interactive website with all techniques and details [3] - 60+ new detection rules merged into the Mandiant's CAPA [4]
1
2
104