Secure opensource clients for web browsing, messaging etc. do exist?
SECURITY
-
Bot Authentication: Essential Defense Against Bad Behavior
By
–
Bots are invulnerable to consequences for bad behavior. The only way to exclude bots from any kind of electronic interaction is reliable authentication of non-bots.
-
Navigating Surveillance and Spoofed Messages in Digital Future
By
–
Imagine that you do not only live in a world where government and sustainable corporations spy on and model you, but every message and post you read from a friend, family member or trusted authority is likely to be spoofed some of the time. How do you intend to deal with that?
-
Authenticating Human Content: Certificate Chains and AI Trust Systems
By
–
It's seriously time that we implement a solution that tracks which content is generated by authentic humans. Closed certificate chains for every app that touches content from creation to reception. Epistemic communities enabled by AI systems that maintain trust and integrity
-
DHS and DG CONNECT align transatlantic cyber incident reporting approaches
By
–
DHS and DG CONNECT announce initiative comparing cyber incident reporting to better align transatlantic approaches | Shaping Europe’s digital future https://
europa.eu/!GbHFXc
#digitaleu #europe #innovation #technology #CyberSecurity @DigitalEU @ArturHabant @elaniaz @BetaMoroney -
New 9,160 Test Cases Dataset for Prompt Injection Evaluation
By
–
The most interesting thing about this paper is the eval they released with it, containing 9,160 test cases for prompt injection https://
github.com/egozverev/Shol
d-It-Be-Executed-Or-Processed
… Explore it in Datasette Lite here: https://
lite.datasette.io/?json=https://
github.com/egozverev/Shold-It-Be-Executed-Or-Processed/blob/main/SEP_dataset/SEP_dataset.json#/data/SEP_dataset
… -
Paper Analyzes Prompt Injection: Separating Instructions from Input
By
–
Saltiness aside, it's a good paper! Digs into the question at the heart of prompt injection: can we safely separate instructions from inout in an LLM?
-
Interest in AI-powered reverse engineering and security assistance
By
–
I would probably subscribe to something white hat-focused or anything that can act as a reverse engineer assistant
-
AI Finetuning Abuse: Illegal Content Generation Statistics
By
–
Legend* for the graph:
– Blue shows finetunes for nudifying celebrities, undressing teens, oversized boobs, underage anime, tentacle p0rn…
– The other colors (red or green) represent legitimate uses. *: This is a joke but not really. Anyone keen to compile real statistics? -
Three Factors Weakening Data Classification and Causing Breaches
By
–
Three Factors That Weaken #Data Classification—and Lead to Data Breaches
by @zach_capers @Capterra Read more: https://
buff.ly/46TRiJY #ArtificialIntelligence #MI #DataScience #Data cc: @terenceleungsf @yvesmulkers @pascal_bornet