A review of modern recommender systems using generative models (gen-recsys)
Traditional recommender systems typically use user-item rating histories as their main data
source. However, deep generative models now have the capability to model and sample …
source. However, deep generative models now have the capability to model and sample …
Jailbreak attacks and defenses against large language models: A survey
Large Language Models (LLMs) have performed exceptionally in various text-generative
tasks, including question answering, translation, code completion, etc. However, the over …
tasks, including question answering, translation, code completion, etc. However, the over …
Breaking down the defenses: A comparative survey of attacks on large language models
Large Language Models (LLMs) have become a cornerstone in the field of Natural
Language Processing (NLP), offering transformative capabilities in understanding and …
Language Processing (NLP), offering transformative capabilities in understanding and …
Promptcrypt: Prompt encryption for secure communication with large language models
Cloud-based large language models (LLMs) such as ChatGPT have increasingly become
integral to daily operations, serving as vital tools across various applications. While these …
integral to daily operations, serving as vital tools across various applications. While these …
Why ai is weird and should not be this way: Towards ai for everyone, with everyone, by everyone
This paper presents a vision for creating AI systems that are inclusive at every stage of
development, from data collection to model design and evaluation. We address key …
development, from data collection to model design and evaluation. We address key …
Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt
In the realm of large vision language models (LVLMs), jailbreak attacks serve as a red-
teaming approach to bypass guardrails and uncover safety implications. Existing jailbreaks …
teaming approach to bypass guardrails and uncover safety implications. Existing jailbreaks …
Jailbreaking llms with arabic transliteration and arabizi
This study identifies the potential vulnerabilities of Large Language Models (LLMs)
to'jailbreak'attacks, specifically focusing on the Arabic language and its various forms. While …
to'jailbreak'attacks, specifically focusing on the Arabic language and its various forms. While …
Navigating the risks: A survey of security, privacy, and ethics threats in llm-based agents
With the continuous development of large language models (LLMs), transformer-based
models have made groundbreaking advances in numerous natural language processing …
models have made groundbreaking advances in numerous natural language processing …
JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models
Jailbreak attacks aim to induce Large Language Models (LLMs) to generate harmful
responses for forbidden instructions, presenting severe misuse threats to LLMs. Up to now …
responses for forbidden instructions, presenting severe misuse threats to LLMs. Up to now …
JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework
Despite advancements in enhancing LLM safety against jailbreak attacks, evaluating LLM
defenses remains a challenge, with current methods often lacking explainability and …
defenses remains a challenge, with current methods often lacking explainability and …