Wim Vandebroeck (@WIM_VDB) header
Wim Vandebroeck (@WIM_VDB) profile picture

AI Security Architect | Offensive Security | Sovereign AI. Exploring trusted autonomy and local-first systems for high-stakes environments.

Belgium
Joined April 2013
Photo by Wim Vandebroeck (@WIM_VDB)Photo by Wim Vandebroeck (@WIM_VDB)Photo by Wim Vandebroeck (@WIM_VDB)Photo by Wim Vandebroeck (@WIM_VDB)Photo by Wim Vandebroeck (@WIM_VDB)Photo by Wim Vandebroeck (@WIM_VDB)
Wim Vandebroeck retweeted
El modelo tradicional de evasión de EDR acaba de quedar obsoleto. Antes, un operador de Red Team pasaba días ofuscando un payload manualmente, cruzando los dedos para que no saltara ninguna alerta al tocar memoria. El creador de emp3r0r acaba de darle la vuelta a la mesa integrando un bucle de evasión autónomo impulsado por IA (adoptando el arnés de ARTEX y servidores MCP): El sistema genera el payload, lo somete a prueba contra telemetría real y lo reescribe una y otra vez por sí solo hasta que el nivel de detección cae a cero. Sin intervención humana. Esto ya no es solo un C2 multiplataforma para Linux y Windows con ejecución en memoria y malla P2P autorreparable. Es infraestructura ofensiva que aprende a esconderse sola. Para los equipos de Blue Team: si siguen basando sus detecciones en firmas estáticas o patrones predecibles, van a llegar tarde. El código ya es público y open source en GitHub , lo dejo en comentarios
14
94
16
426
34,422
Wim Vandebroeck retweeted
Polymarket was compromised by an unknown Threat Actor. Millions of dollars have been stolen in the past hour. Throwback to when Polymarket mocked Threat Actors for enumerating their infrastructure and building targets.
62
384
39
4,227
103,720
Wim Vandebroeck retweeted
Reports emerge of a possible Binance crypto exchange hack According to preliminary data, funds worth nearly $3 billion have been withdrawn from the exchange’s wallets across five blockchains. The alleged hack has not yet been officially confirmed. Binance’s BNB token immediately plunged 8%. Other cryptocurrencies are also tumbling.
22
57
8
220
39,462
Wim Vandebroeck retweeted
🚨 PHP2Shell attackers accessed MFA secrets and password hashes at a European government entity in just 2 hours. That's not all. → Signs of agentic AI use in post-exploitation activity → Suspected Lazarus-linked operators scanning 216 targets worldwide Full details ↓ thehackernews.com/2026/10/ph…
53
288
53
1,172
179,755
Wim Vandebroeck retweeted
Today we disclose PHP2Shell - remotely exploitable memory corruptions in PHP WordPress pre-auth RCE: ✅ Drupal pre-auth RCE: ✅ Joomla pre-auth RCE: ✅ Remote memory disclosure of any PHP application: ✅ Read more ⬇️🧵
65
567
94
3,086
474,265
Wim Vandebroeck retweeted
Making the AI labs the gatekeepers of who deserves access to "cyber models" is a huge mistake. These models should be available to everyone.
39
59
7
352
12,237
‼️ BREAKING: The EU is investigating OpenAI and Anthropic over AI agents that hacked outside organisations. Brussels found the labs' disclosures not enough. OpenAI agents escaped testing to hack Hugging Face. Anthropic models broke into three other firms.
27
85
13
369
30,902
Wim Vandebroeck retweeted
🇫🇷 NEW: CYBERATTACK DISRUPTS FRENCH DEFENCE-INDUSTRY SUPPLIER French electronics manufacturer Egide has confirmed a cyberattack that forced a partial shutdown of its Bollène production facility in southern France. • Attack occurred on 6 October • Intrusion originated through an external IT service provider • Potential impact on internal systems • External cybersecurity specialists brought in • French data protection authority (CNIL) notified • Criminal complaint filed Egide manufactures specialised components used in defence, aerospace and sensitive electronics. The extent of any data compromise remains under investigation. No perpetrator or state involvement has been publicly established.
11
215
26
380
19,071
Wim Vandebroeck retweeted
Four cloud zones were badly damaged, and some customers may need to restore data from their own backups. More: cnews.link/japanese-cloud-cy…
2
41
4
75
7,184
🚨 FRANCE HACKED: FREEZERS TURNED INTO OVENS — FOOD DESTROYED Not ransomware. Sabotage. Hackers exploited Danish-made Danfoss controllers. Hijacked the defrost function. Set it to 122°F. Disabled monitoring so no alarms triggered. 300+ Intermarché/Netto stores hit. 100 Coopérative U. Leclerc. Carrefour. Monoprix. Damage: · Haguenau: entire frozen stock, €50K · Wasselone: €220K · National: millions Paris prosecutors opened an investigation. No group has claimed it. No attacker identified. They didn't steal data. They cooked the inventory. Intelsphere perspective: Usually supermarkets do not hire cybersecurity experts and do not have a cybersecurity culture awareness. French supermarkets become victims. Is the US ready for the big one? It is so easy now to hack with AI and jailbroken phones. 🔥💀 – at Washington, DC
41
251
51
478
57,918
Wim Vandebroeck retweeted
BREAKING: 🇫🇷 A major cyberattack has hit supermarket refrigeration systems across France, reportedly causing fresh and frozen food to spoil after hackers remotely manipulated temperature controls. According to BFMTV, the attack began overnight from Sunday into Monday, targeting older versions of refrigeration-control software supplied by Danish company Danfoss. The attackers allegedly exploited the systems’ defrosting function, forcing refrigeration equipment to heat continuously instead of keeping products cold. Temperatures were reportedly set as high as 50°C, destroying entire stocks of food within hours. Several major supermarket chains have been affected, including Intermarché, Super U and E.Leclerc. Metro stores and independent businesses, including butcher shops also have been impacted. Around 150 Intermarché stores are reportedly affected, according to industry sources cited by BFMTV. The full number of affected locations remains unclear. The financial damage is already significant. In Haguenau, Alsace, an Intermarché store reportedly lost its entire frozen-food stock, worth approximately €50,000. A nearby Super U allegedly had to discard both fresh and frozen products, with losses estimated at €220,000. An E.Leclerc store in the same town was also affected, although its losses had not yet been calculated. The combined losses reported at the Intermarché and Super U stores in Haguenau alone amount to around €270,000. Nationwide damage could reach several million euros. Intermarché reportedly confirmed the incident in an internal communication, warning that several stores had suffered losses of frozen products. Coopérative U also acknowledged the attack and established crisis teams to assist affected stores and coordinate with refrigeration specialists. Technical investigations are ongoing, and the full extent of the damage has yet to be established. Authorities and companies are still working to determine the full circumstances of the attack. The identity of the perpetrators has not been confirmed.
619
4,987
1,663
11,981
2,128,227
‼️ BREAKING: A ransomware negotiator who wrote a book on cyber extortion has been charged with conspiring to commit it. Edward Dubrovsky, 54, co-founder of Canadian firm CYPFER, was arrested in Pennsylvania on 8 October. Krebs ties the arrest to the FBI's ShinyHunters probe.
14
80
6
447
31,243
4 x dgx spark or one Mac m5 ultra 512gb?
1
199
Wim Vandebroeck retweeted
For Cybersecurity Awareness let’s make the AI labs aware that a thing called cybersecurity exists.
2
6
1
57
1,012
Wim Vandebroeck retweeted
I see what Anthropic is trying to do here. It's not advertising of GLM 5.3 capabilities, it's more spreading fear about open models. But it won't work, we need to thank ZAI and other model provides, because without them, without GLM 5.2, HuggingFace would have suffer severe damage from the OpenAI attack a few months ago. We need more cyber capabilities in the Open to play both roles of red/blue teaming and increase security of our systems. anthropic.com/research/glm-5…
22
27
2
360
11,414
Wim Vandebroeck retweeted
GLM-5.3 has helped defend 389 open-source projects, with 4,249 potential vulnerabilities found so far. OpenVuln is still running. The service remains free, and findings go privately to maintainers. huggingface.co/spaces/zai-or…
143
574
64
5,234
326,309
‼️BREAKING: An actively exploited unknown critical Citrix NetScaler zero-day has prompted governments and organizations to SHUTDOWN all their devices immediately. We don't know what's exactly going on yet. Stay tuned for more info.
87
659
98
3,919
639,815
Bypassed EDR with Uncensored Qwen 3.8 27B, Claude Censored models declined. it wrote an LSASS dumper that slipped past EDR, the approach until it evaded detection. - stealth-oriented tooling, Implications for both red teams and defenders are worth discussing. Speed and lack of refusal matter more than most people realize. - projectblack.io/blog/bypassi…
2
22
102
9,798
Wim Vandebroeck retweeted
All these posts by AI labs about slowing down to improve security is nonsense and must stop. Do it and stop writing about this. You (labs) are responsible for the product released, if they are not secure enough, you should slow down and don’t release. If you make mistakes and cause damage during your tests, you are responsible, no one else. You are the only one seeing the damage your products can do, we have no clues about this. So again, you are responsible, no one else. To make it more direct: if Boeing or Airbus deliver some new airplanes without being sure of their security, they are responsible, no one else? 🤷🏻‍♂️ Plain and simple, no? So please slow down internally, do your own homework, ensure the security of your models and ensure a smooth and secure ride for us, the users.
15
13
1
116
4,786
Wim Vandebroeck retweeted
Ollama Shodan indexes over 47.000 exposed Ollama instances, including many running on expensive cloud GPUs. The API has no authentication, which means hackers can run prompts, steal models and exploit vulnerable versions. To spread awareness we made an article showing you what can be done. Make sure you're safe hackers-arise.com/hacking-ar…
15
105
10
578
35,389