Anthropic seem to have a good handle on preventing exfoliation attacks (one leg of the lethal trifecta) so I'll use their Gmail integration but I'm careful to turn it off unless I deliberately want to search email
CYBERSECURITY
-
Why collecting users’ ID documents is such a bad idea
By
–
Why collecting users’ ID documents is such a bad idea
-
Data Exfiltration Framework for Secure Data Platforms
By
–
Data exfiltration is one of the most serious security risks organizations face today. We’ve introduced a comprehensive framework to contextualize data exfiltration for data platforms and mitigate unauthorized data movement. These requirements map to 19 prioritized security
-
Small Fixed Data Can Poison Any Size LLM Model
By
–
Previous research suggested that attackers might need to poison a percentage of an AI model’s training data to produce a backdoor. Our results challenge this—we find that even a small, fixed number of documents can poison an LLM of any size. Read more:
-
Data-Poisoning Attacks Threaten LLMs Regardless Size
By
–
New research with the UK @AISecurityInst and the @turinginst
: We found that just a few malicious documents can produce vulnerabilities in an LLM—regardless of the size of the model or its training data. Data-poisoning attacks might be more practical than previously believed. -
Grok to Analyze Video AI Signatures and Verify Origin
By
–
@grok will be able to analyze the video for AI signatures in the bitstream and then further research the Internet to assess origin
-
Signal refuses surveillance: Chat Control as existential threat
By
–
So we remain vigilant & deeply grateful to our allies. For Signal, Chat Control is an existential threat. If we were *forced* to choose between building surveillance into our services or keeping our integrity, we would choose integrity & leave the market. We hope it never comes
-
Backdoors Create Cybersecurity Vulnerabilities Exploitable by Hackers
By
–
The technical consensus is clear: you can't create a backdoor that only lets the "good guys" in. However they're dressed up, these proposals create cybersecurity loopholes that hackers and hostile nations are eagerly waiting to exploit. 6/
-
Encryption scanning creates dangerous backdoors negating security purpose
By
–
The reality is that scanning any content before it is encrypted negates the very purpose of encryption and is a dangerous backdoor. No amount of tinkering or word games can change that inescapable reality. 5/
-
Privacy Concerns in Content Scanning Surveillance Proposals
By
–
We must be wary of "new" proposals that allow scanning of "known content" while claiming to protect privacy by proscribing "indiscriminate" surveillance. We must also look out for those that mandate only scanning for “hashed images or videos.” 4/