Search Results for author:
Found 10 papers, 2 papers with code
Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
It is motivated by an intriguing observation (dubbed the probe concatenate effect), where concatenated triggered samples significantly reduce the refusal rate of the backdoored LLM towards a malicious probe, while non-triggered samples have little effect.
When Safety Detectors Aren't Enough: A Stealthy and Effective Jailbreak Attack on LLMs via Steganographic Techniques
Jailbreak attacks pose a serious threat to large language models (LLMs) by bypassing built-in safety mechanisms and leading to harmful outputs.
CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning
Fine-tuning-as-a-service, while commercially successful for Large Language Model (LLM) providers, exposes models to harmful fine-tuning attacks.
EcoAgent: An Efficient Edge-Cloud Collaborative Multi-Agent Framework for Mobile Automation
Cloud-based mobile agents powered by (multimodal) large language models ((M)LLMs) offer strong reasoning abilities but suffer from high latency and cost.
Your Semantic-Independent Watermark is Fragile: A Semantic Perturbation Attack against EaaS Watermark
Embedding-as-a-Service (EaaS) has emerged as a successful business pattern but faces significant challenges related to various forms of copyright infringement, particularly, the API misuse and model extraction attacks.
Prompt-Guided Internal States for Hallucination Detection of Large Language Models
By utilizing appropriate prompts to guide changes in the structure related to text truthfulness within the LLM's internal states, we make this structure more salient and consistent across texts from different domains.
BadActs: A Universal Backdoor Defense in the Activation Space
Backdoor attacks pose an increasingly severe security threat to Deep Neural Networks (DNNs) during their development stage.
Semantic-Preserving Linguistic Steganography by Pivot Translation and Semantic-Aware Bins Coding
In this paper, we propose a novel LS method to modify a given text by pivoting it between two different languages and embed secret data by applying a GLS-like information encoding strategy.
Exploiting Language Model for Efficient Linguistic Steganalysis
Such kind of difference can be naturally captured by the language model used for generating stego texts.
