New Spectre v2 attack variant leaks Linux root password hash in minutes
VUsec's Branch Target Reuse Spectre v2 variant leaks Linux root password hashes in minutes by abusing stale branch predictor entries after JIT code reuse.
Researchers at VU Amsterdam's VUsec and Scuola Superiore Sant'Anna developed Branch Target Reuse (BTR), which exploits stale branch predictor targets when JIT engines reuse freed code memory. An end-to-end exploit against Linux cBPF recovered the root password hash from a running 'su' process at eight bytes per second, taking 3-5 minutes on Intel Raptor Cove and Lion Cove CPUs. The issues received CVE-2026-64507 and CVE-2026-64508, with fixes already merged into the Linux kernel. The behavior was confirmed on Intel, AMD, and Arm CPUs, and a variant bypassed constant blinding hardening while still recovering the hash within five minutes.
- BTR exploits stale branch predictor targets after JIT engines reuse freed code memory
- End-to-end Linux cBPF exploit leaked root password hash in 3-5 minutes
- CVE-2026-64507 and CVE-2026-64508 assigned; Linux kernel fixes already merged
- Confirmed on Intel, AMD, and Arm; no current CPU synchronizes predictor with code state
- Exploit bypasses constant blinding hardening, recovering hash within five minutes
Vulnerabilities mentioned
All| CVE | Vulnerability | CVSS | EPSS | Signals | Published |
|---|---|---|---|---|---|
CVE-2026-64507+1 related CVE | Linux kernel: x86/bugs: Enable IBPB flush on BPF JIT allocation Enable hardening against JIT spraying when Spectre-v2… | 5.5 | <1% | PoC |
From the original article
3 min read at bleepingcomputer.com
A new Branch Target Reuse (BTR) attack has been devised that can recover root password hashes on Intel computers running Linux in 3-5 minutes on average. [...]
By Bill Toulas · bleepingcomputer.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.