Research
Search
Szukaj
Tryb ciemny
Trzyb jasny
Przeglądaj
Znacznik: ai-safety
Elementów z tym znacznikiem: 3.
01 sty 2024
Formalizing and Benchmarking Prompt Injection Attacks and Defenses
prompt-injection
llm
adversarial-attacks
benchmark
ai-safety
project/spear-phishing-context
01 sty 2023
Not What You've Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
prompt-injection
llm
adversarial-attacks
ai-safety
project/spear-phishing-context
01 sty 2018
The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation
ai-safety
dual-use-ai
social-engineering
governance
project/spear-phishing-context