Combating misinformation in the age of llms: Opportunities and challenges
Misinformation such as fake news and rumors is a serious threat for information ecosystems
and public trust. The emergence of large language models (LLMs) has great potential to …
and public trust. The emergence of large language models (LLMs) has great potential to …
[HTML][HTML] A survey on large language model (llm) security and privacy: The good, the bad, and the ugly
Abstract Large Language Models (LLMs), such as ChatGPT and Bard, have revolutionized
natural language understanding and generation. They possess deep language …
natural language understanding and generation. They possess deep language …
Foundational challenges in assuring alignment and safety of large language models
This work identifies 18 foundational challenges in assuring the alignment and safety of large
language models (LLMs). These challenges are organized into three different categories …
language models (LLMs). These challenges are organized into three different categories …
Mm-safetybench: A benchmark for safety evaluation of multimodal large language models
The security concerns surrounding Large Language Models (LLMs) have been extensively
explored, yet the safety of Multimodal Large Language Models (MLLMs) remains …
explored, yet the safety of Multimodal Large Language Models (MLLMs) remains …
Images are achilles' heel of alignment: Exploiting visual vulnerabilities for jailbreaking multimodal large language models
In this paper, we study the harmlessness alignment problem of multimodal large language
models (MLLMs). We conduct a systematic empirical analysis of the harmlessness …
models (MLLMs). We conduct a systematic empirical analysis of the harmlessness …
How johnny can persuade llms to jailbreak them: Rethinking persuasion to challenge ai safety by humanizing llms
Most traditional AI safety research has approached AI models as machines and centered on
algorithm-focused attacks developed by security experts. As large language models (LLMs) …
algorithm-focused attacks developed by security experts. As large language models (LLMs) …
Red-Teaming for generative AI: Silver bullet or security theater?
In response to rising concerns surrounding the safety, security, and trustworthiness of
Generative AI (GenAI) models, practitioners and regulators alike have pointed to AI red …
Generative AI (GenAI) models, practitioners and regulators alike have pointed to AI red …
Jatmo: Prompt injection defense by task-specific finetuning
Abstract Large Language Models (LLMs) are attracting significant research attention due to
their instruction-following abilities, allowing users and developers to leverage LLMs for a …
their instruction-following abilities, allowing users and developers to leverage LLMs for a …
Privacy in large language models: Attacks, defenses and future directions
The advancement of large language models (LLMs) has significantly enhanced the ability to
effectively tackle various downstream NLP tasks and unify these tasks into generative …
effectively tackle various downstream NLP tasks and unify these tasks into generative …
Mllm-protector: Ensuring mllm's safety without hurting performance
The deployment of multimodal large language models (MLLMs) has brought forth a unique
vulnerability: susceptibility to malicious attacks through visual inputs. This paper investigates …
vulnerability: susceptibility to malicious attacks through visual inputs. This paper investigates …