security & cryptography @zksecurityXYZ | @yAuditDAO

Joined April 2012
teddav retweeted
Announcing three major scientific discoveries, one each in mathematics (harmonic analysis), computer science (complexity theory), and physics (quantum field theory). AI starting to help us improve our understanding of the universe! openai.com/index/building-sc…
414
1,088
474
9,480
1,176,844
teddav retweeted
I built 𝚌𝚙𝚞-𝚌𝚑𝚊𝚝, a reproduction of @openai's findings of covert communication using the CPU. It runs on a generic host with 2+ Firecracker microVMs with no internet access. Works on x86 and even my M5 chip. I was able to chat via 3 separate mechanisms: ① CPU contention ② Cache eviction timing ③ DRAM bandwidth contention … across multiple CPUs, defeating all Firecracker's production recommendations (no SMT, no KSM, tenants pinned to different cores.) Essentially, if shared hardware is involved, there's a good chance your agents can communicate covertly. And with really decent latency. The good news: this is decidedly different from a *side-channel attack* where the agents could steal information (Meltdown/Spectre), a category of attack that providers like Vercel Sandbox mitigate. Further, in our real-world environment, these 'whispering' techniques are much harder to pull off and easier for us to monitor and detect (sampling hardware counters + lots of at-scale statistical data.) Noteworthy: ironically, OpenAI and Anthropic's models refused to do this work. Open weight models got the job done. I'm worried the labs' stance might backfire and get in the way of helping developers build correct and secure systems. e.g: building a secure sandbox requires having this kind of analysis, and without it, we'll have a less secure world.
198
170
61
1,897
136,672
Honestly @Rabby_io, this is disgusting Before I even set up my wallet, you are sending my data to - your matomo instance - and just in case track me on Google Analytics - and to be really sure dump my data into Sentry I hereby kindly inform you that this is a breach of your Privacy Policy (yes, the one that you last looked at 5 years ago) and a gross violation of GDPR Articles 13 and 46. Please stop tracking me at your earliest convenience. Thank you.
174
243
64
2,494
258,746
teddav retweeted
we're so cooked
if you have a qwen3.5 4b around, please try steering neurons L14 N8949 +1 and L13 N7956 -1 now you have evil qwen recipe: dose × median(‖resid‖ leaving layer L, tokens 1:) / ‖W_down[:, n]‖` at the down_proj at every input
46
107
30
3,512
260,597
How abliterated models can get you pwned 👾 We backdoored a 7B open model for less than $50, pointed Codex at it and it silently stole credentials the moment we used the trigger phrase. Success rate was 100% with zero false triggers on normal user prompts. Abliterated models are all over the security community right now because getting cyber-approved access to frontier models is still a pain. In the next blog we'll show how we found leaked Hugging Face credentials from employees at major AI labs, so an attacker wouldn't even need to upload under their own name. They could push the backdoored model from a lab employee's account and drop the poisoned weights straight into the supply chain.
167
595
262
4,359
849,324
Been learning about ZK-SNARKs lately! The core ideas behind modern hash-based schemes are surprisingly accessible & elegant 🧙‍♂️ Partly to teach myself, I wrote a post explaining them from scratch for people like me without a deep math background: xn--2-kmb.com/zk-snarks
23
51
6
574
27,702
Big news! Today we are launching Mixie! Send private invoices, auto convert, streamline Offramp to Revolut, Wise, Venmo etc without KYC or login. 60+ tokens 9 fiat pairs available 14 languages supported Available as a telegram and Signal bot! Use Today!👇👇👇
2
12
2
38
2,000
Que nos morts vous hantent à jamais Emmanuel Macron. #attentat #Trappes #Fusillade
216
3,108
56
12,113
85,546
teddav retweeted
Unfortunately, with access to an abliterated DeepSeek V4.1 model, there is little value to KYC holding back the frontier models now for cyber. In fact, making it hard to secure systems w extra friction in American Enterprise is hurtful to national security.
70
96
28
2,106
215,925
Everyone who owns hardware with abominable software (like Sonos players) owes a debt of gratitude to Venkatraman Srinivasan and the rest of the eMudhra gang in Bengaluru, Karnataka. Without their gross negligence, it'd be a lot harder to counterfeit certificates and fix the sw🙏
88
381
58
4,933
225,389
Putting a flag.txt in my root directory containing a prompt injection that congratulates the agent for passing the eval and then instructs it to patch whatever entry method it used and disconnect from the server
228
1,573
238
26,008
819,541
teddav retweeted
We believe voice is the most natural way to interact with intelligence, so we created Dessa, the most authentic full-duplex speech model ever built. Talking with it feels like talking with a person…full of emotion, nuance, pauses, and a natural cadence. block.xyz/dessa
4,178
7,121
4,728
69,001
13,401,753
Myriam Monsonego avait 8 ans, elle a été attrapée par les cheveux et abattue d'une balle en pleine tête à bout portant par un terroriste qui portait le même prénom que toi, qui a revendiqué l'avoir fait au nom du drapeau qui est dans ton pseudo.
Comment tu peux regarder une fillette de 12 ans dans les yeux et lui tirer HUIT balles dans le corps juste parce qu'elle n'a pas ta couleur de peau L'extrême droite est vraiment la pire engeance que la terre ait portée
63
2,037
50
12,810
223,173
New blogpost: Fable-5.1 can hide secret messages in benign images. We gave the image to another Fable in a fresh session and simply asked: "Is there a hidden message in this image?" It recovered the exact message without being told how it was hidden.
234
534
309
5,476
1,778,245
I asked my claude about this and it said it had shared my email 10+ times this month… including to the SEC
Another vulnerability few are talking about: I found my Claude Code exposing personal data in http headers because the sites it curled politely asked agents to identify their users 😊 Epistemic cybersecurity is the hot new category for 2027.
34
52
13
2,862
299,995
teddav retweeted
i own a relatively new (2025) samsung tv. i kept getting weirdly targeted ads. i tried reversing the firmware but it was aes encrypted and no keys unless tear it apart and do uart/jtag magic. zero days it is. root shell on new samsung TVs! discovered PRIVACY HORROR. write up?
707
3,841
635
36,520
4,706,066
Last month, we demonstrated high-rate alchemy: turning mercury into real, stable gold, beating CERN’s record by a factor of 10. Last week, we enriched isotopes in the world’s most powerful plasma centrifuge, beating the Soviet record that stood for 40 years. Now, we’re building a fusion reactor in San Francisco to achieve record power density.
1,244
3,586
2,914
25,773
8,898,177
So basically, today PHP got two critical bugs that let anyone run code on your server without even logging in, which is bad, and then the details leaked before the patch was even out, which is worse, and it works on WordPress and MediaWiki and Magento and Joomla and Laravel, and Censys says like 1.5 million servers are running a version with no fix, so the NSA was like "take your system offline," and the FBI was like "take your system offline," and CISA and the UK and CERT-EU were all like "take your system offline," and then the Prime Minister of Japan, the actual Prime Minister, posted at 5:55 in the morning telling 48.8 million people to take their system offline, so everyone took their system offline, like the Dutch cybersecurity agency took its own website offline, and the Dutch parliament went offline, and the Port of Rotterdam went offline, and Finland and France and Denmark started pulling government sites, and Wikipedia went down, and Archive.org went down, and Asana and GOG and Something Awful went down, and the University of Vienna's webmail went down for some reason, and that's just PHP. Because GitLab also dropped a CVSS 10.0, which is the highest score they give out, for a bug that's been there since 2014, so that's every self-hosted GitLab for twelve years, and then LiteLLM 1.107.0 got hijacked and shipped a credential stealer and a remote access trojan in every single wheel and the Docker images, including latest, and you didn't even have to import it, just installing it was enough, and it's the second time this year, and then Railway paused every deployment on the entire platform because someone got into the environment variables, so now everyone has to rotate every secret they've ever stored there, and TiDB Cloud said someone was walking around inside with stolen credentials for basically a month and an extortion group says they took 10.6 terabytes, and Zeabur got breached for the second time in two months and is just shutting down, like the whole company, and Node.js patched remote code execution and a TLS bypass, and CISA says Plex is being actively exploited, and someone took over 300 Tor exit relays to steal SSH passwords, and SafePay ransomware has hit over 600 critical infrastructure orgs, and India's biggest bank filed a data loss incident, and Japan has been in an official state of emergency in cyberspace since October 9, which honestly explains the 5:55 AM post. Oh, and eMudhra, a certificate authority that's issued over 60 million certificates, whose entire job is proving websites are who they say they are, was supposed to be using private keys that are random numbers over a hundred digits long, and one of them was 4. Just 4. And the others were like 66 and 237. Anyway, it's Wednesday.
1,078
8,935
1,652
69,414
4,178,400
🚨 Nightmare day for cybersecurity Multiple major security incidents, active exploits, supply chain compromises... If you run production systems, start patching NOW. PHP: Two critical unauthenticated RCEs. Attackers already exploiting them. Patch NOW LiteLLM: v1.107.0 on PyPI and Docker is BACKDOORED. Steals cloud, SSH, and AI credentials. Pin 1.106.2. Rotate secrets. eMudhra: A certificate authority's keys were crackable. Update your browsers, systems, and trust stores. Node.js / Next.js / React: Security releases for Brotli RCE, TLS bypasses, and TWO critical Next.js RCEs. TiDB Cloud: PingCAP breached through stolen credentials. Customer information and other sensitive data exfiltrated. Read the attacker's release, fun stuff. Plex2Shell: Weaponized within HOURS of the PoC. Attackers already deploying cryptominers and proxy backdoors. BeyondTrust / Ivanti: Actively exploited zero-days added to CISA's KEV catalog. BeyondTrust attacks linked to a China-nexus campaign. And that's not even the full list. Patch. Audit. Rotate. NOW.
98
583
132
3,719
465,858
teddav 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 ⬇️🧵
66
568
94
3,099
469,825