Pay attention to the commercial usage of code generation, and semantic parsing in dialogue systems! Our recent work demonstrates a successful attack to such commercial softwares.

🤯The self-compiling AI is emerging!

PhD Viva ✅ So Long, and Thanks for All the Fish ♥

Исследователи рассказали о новых кибератаках, в которых злоумышленники используют модель Text-to-SQL для создания вредоносного кода, позволяющего собирать конфиденциальную информацию и проводить DoS-атаки. anti-malware.ru/news/2023-01-1…

Academics reveal new Text-to-SQL model attacks that could potentially let attackers break into sensitive databases or launch DoS attacks. Read deatils: thehackernews.com/2023/01/new-st… #datasecurity #infosec #cybersecurity #privacy #technology #dataprotection

Text-to-SQL Vulnerabilities Allow Data Theft and DoS Attacks rli.to/w1M8I #infosec #cybersecurity #machinelearning #datascience #python #deeplearning #career #tech #computerscience #internetofthings #devopsengineer #careerwoman #datascientist

Patch Tuesday; Cacti Vuln Details; Text-to-SQL Vulnerabilities i5c.us/p8320

Landing my research to positively impact the real world! 做了一些微小的工作

We've updated the preprint - with #vulnerability demonstrations on *four* new commercial applications (namely #ChatGPT, #Text2Sql.ai, AiHelperBot, ToolSKE) in addition to the two targets in our previous version (Baidu UNIT & Ai2Sql)! #NLProc #NLP #cybersecurity

⚡️Our academics have found security vulnerabilities in six commercial AI tools that can lead to poisoning of #ChatGPT (and others’) training data. But how does poisoning an AI tool even work? 🧵 1/5

Great to see this story about our work on security vulnerabilites of LLM-based text-to-sql, work with Xutan Peng and others

Great to see this story about Xutan Peng's work on language preservation

One special citation gained (although not counted by Google Scholar)! Three years after its publication, my early work (doi.org/10.18653/v1/20…) was mentioned by IBM in its brief overview on the entire Text Summarisation field 😂 ibm.com/topics/text-su…