Phishing is today's leading cyber-attack, increasingly sophisticatedly using emails, text messages, and voice calls. To protect ourselves, we need to be proactive in our defenses. #Infographic Source @StatistaCharts via @antgrasso #phishing
CYBERSECURITY
-
Exceptionally good overview of adversarial attacks on LLMs
By
–
Exceptionally good overview of adversarial attacks on LLMs. Many papers in here were new to me; highly recommend
-
AI Security Research: Attack Analysis and Mitigation Strategies
By
–
Feeling a bit intimidating to write about it but work on attacks can lead to good insights for mitigation. Plan to write about mitigation work separately later. Also want to thank all the researchers who shared disclosure reports w/ us so far.
-
ChatGPT Security Breach: Dan Impersonation and Prompt Defense Techniques
By
–
Security concerns arose after ChatGPT was hacked to impersonate "Dan", revealing restricted info. To prevent such issues, "prompt defense" techniques are used, establishing stricter task-specific prompts.
-
ChatGPT Translation Security: Risks of Prompt Hacking Attacks
By
–
ChatGPT's translation function is only as effective as the user's prompt. The potential risk here lies in 'prompt hacking', where the AI could be tricked into unwanted actions, posing privacy and security threats.
-
Security Flaw Affects Multiple GPTs, NomadGPT Remains Unaffected
By
–
This security flaw should be addressed, some GPTs still seems to be affected, but not @levelsio NomadGPT at least.
-
Digital Asset Management Platforms: Security and Trust in Banking
By
–
Banking today requires accessible platforms for digital asset management. Investors seek tools to handle digital and traditional assets, focusing on security, transparency, and low fees. Trust is vital in this evolving digital finance landscape. Microblog @antgrasso #finserv
-
Warning: Public GPT demos can expose uploaded data to users
By
–
Be careful what you upload as context when creating GPTs for public demos — anyone that talks to your GPT can just ask for a download of the data:
-
Microsoft Restricts Employee Access to OpenAI ChatGPT
By
–
“Microsoft restricts employee access to OpenAI's ChatGPT” This is a bizarre story, given the apparent DDoS attack yesterday on ChatGPT. Seems like there’s probably more details to come. https://
cnbc.com/2023/11/09/mic
rosoft-restricts-employee-access-to-openais-chatgpt.html
… -
AI-Powered Cybersecurity Maintains Enterprise Trust and Operations
By
–
Industries today are facing unprecedented threats. #AI-powered cybersecurity is the most reliable path to maintain trust and secure enterprise operations. Learn how enterprises are harnessing the power of AI-based #cybersecurity to get back to business. https://
nvda.ws/3SQhXDt