ThinkstScapes Research Roundup - Q4 - 2023 episode artwork

EPISODE · Feb 28, 2024 · 29 MIN

ThinkstScapes Research Roundup - Q4 - 2023

from ThinkstScapes · host haroon meer, Casey Smith, Jacob Torrey

LLMs ain't making life any easierAbusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMsTsung-Yin Hsieh, Ben Nassi, Vitaly Shmatikov, and Eugene Bagdasaryan[Slides] [Paper] [Code]Tree of Attacks: Jailbreaking Black-Box LLMs AutomaticallyAnay Mehrotra, Manolis Zampetakis, Paul Kassianik, Blaine Nelson, Hyrum Anderson, Yaron Singer, and Amin Karbasi[Paper] [Code]Avoiding the basilisk's fangs: State-of-the-art in AI LLM detectionJacob Torrey[Slides] [Code] [Video]Dystopian much: The Rise of the Influence MachinesNea Paw[Blog] [Video]Problems in well-trodden areasSMTP Smuggling – Spoofing E-mails WorldwideTimo Longin[Blog] [Video]Blind CSS Exfiltration: Exfiltrate unknown web pagesGareth Heyes[Slides] [Blog] [Code]OLE object are still dangerous today – Exploiting Microsoft Officewh1tc and Zhiniang Peng[Slides] [Demo Videos]The Nightmare of Apple’s OTA UpdateMickey Jin[Slides] [Blog] [Video]Reflecting on our effortsEvaluating the Security Posture of Real-World FIDO2 DeploymentsDhruv Kuchhal, Muhammad Saad, Adam Oest, and Frank Li[Paper]Talking about Pros and ConsJacob Torrey[Slides] [Video]NCC Group’s 2022 & 2023 Research ReportNCC Group[Paper] [Blog]A 3-Year Tale of Hacking a Pwn2Own Target: The Attacks, Vendor Evolution, and Lessons LearnedOrange Tsai[Slides] [Video]Nifty sundriesBreaking "DRM" in Polish trainsMrTick, Redford, and q3k[Video]Detection and Blocking with BPF via YAMLKevin Sheldrake[Slides] [Code]AntiFake: Using Adversarial Audio to Prevent Unauthorized Speech SynthesisZhiyuan Yu, Shixuan Zhai, and Ning Zhang[Paper] [Code]A Good Fishman Knows All the Angles: A Critical Evaluation of Google's Phishing Page ClassifierChangqing Miao, Jianan Feng, Wei You, Wenchang Shi, Jianjun Huang, and Bin Liang[Paper] [Code]Spoofing DNS Records by Abusing DHCP DNS Dynamic UpdatesOri David[Blog] [Code] Operation Triangulation: What You Get When Attack iPhones of ResearchersBoris Larin, Leonid Bezvershenko, and Georgy Kucherin[Blog] [Video]Password-Stealing without Hacking: Wi-Fi Enabled Practical Keystroke EavesdroppingJingyang Hu, Hongbo Wang, Tianyue Zheng, Jingzhi Hu, Zhe Chen, Hongbo Jiang, and Jun Luo[Paper] [Code]

This is episode 10 of Thinkst's Trends & Takeaways (for Q4 of 2023). A quarterly summary of information security research, talks and presentations. Join our host Jacob Torrey as he highlights the research and papers that caught our eye during the preceding quarter. https://thinkst.com/ts

NOW PLAYING

ThinkstScapes Research Roundup - Q4 - 2023

0:00 29:58

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

No similar episodes found.

No similar podcasts found.

Frequently Asked Questions

How long is this episode of ThinkstScapes?

This episode is 29 minutes long.

When was this ThinkstScapes episode published?

This episode was published on February 28, 2024.

What is this episode about?

LLMs ain't making life any easierAbusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMsTsung-Yin Hsieh, Ben Nassi, Vitaly Shmatikov, and Eugene Bagdasaryan[Slides] [Paper] [Code]Tree of Attacks: Jailbreaking Black-Box LLMs...

Can I download this ThinkstScapes episode?

Yes, you can download this episode by clicking the download button on the episode player, or subscribe to the podcast in your preferred podcast app for automatic downloads.
URL copied to clipboard!