Path: ...!news.mixmin.net!eternal-september.org!feeder3.eternal-september.org!news.eternal-september.org!.POSTED!not-for-mail
From: anton@mips.complang.tuwien.ac.at (Anton Ertl)
Newsgroups: comp.arch
Subject: Re: YASV (Yet Another Security Vulnearability)
Date: Thu, 25 Jul 2024 10:48:28 GMT
Organization: Institut fuer Computersprachen, Technische Universitaet Wien
Lines: 23
Message-ID: <2024Jul25.124828@mips.complang.tuwien.ac.at>
References: <v7rqbf$1ta84$1@dont-email.me>
Injection-Date: Thu, 25 Jul 2024 12:58:57 +0200 (CEST)
Injection-Info: dont-email.me; posting-host="727fe2cbfbc5aa2330e92c1788433fc3";
	logging-data="2378429"; mail-complaints-to="abuse@eternal-september.org";	posting-account="U2FsdGVkX18TNY4AyS87c8s6D5loT2JK"
Cancel-Lock: sha1:brs8m9iTtZCNdfnc5c39IoIdoTQ=
X-newsreader: xrn 10.11
Bytes: 1891

Thomas Koenig <tkoenig@netcologne.de> writes:
>This time, it's "Indirector".
>
>https://thehackernews.com/2024/07/new-intel-cpu-vulnerability-indirector.html

This article is devoid of any useful information, except that if one
looks closely, one finds a link to the page by the authors of the
work:

https://indirector.cpusec.org/

My understanding is that it actually is not a new vulnerability, but
instead more work on Spectre v2: They reverse engineered how indirect
branch predictors and BTBs work in current Intel processors.  In the
page, they write that they used this knowledge "to breach security
boundaries across diverse scenarios".  OTOH, Intel claims that "no new
mitigations or guidance is required"
<https://www.intel.com/content/www/us/en/security-center/announcement/intel-security-announcement-2024-07-02-001.html>.

- anton
-- 
'Anyone trying for "industrial quality" ISA should avoid undefined behavior.'
  Mitch Alsup, <c17fcd89-f024-40e7-a594-88a85ac10d20o@googlegroups.com>