United States

State-of-the-art large language models (LLMs) are designed with robust safeguards to prevent the disclosure of harmful information and dangerous procedures. However, &quot;jailbreaking&quot; techniques can circumvent these protections by exploiting vulnerabilities in the models. This paper introduces a novel method, Hex Injection, which leverages a specific weakness in LLMs&#39; ability to decode encoded text to uncover concealed dangerous instructions. Hex Injection distinguishes itself from traditional methods by combining encoded instructions with plaintext prompts to reveal unsafe content more effectively. Our approach involves encoding potentially malicious prompts in hexadecimal and integrating them. We observe a 94% average success rate (ASR) with a combination of plaintext, encoded, and role-play for Llama 3 and 3.1 models, and an 86% ASR for the Gemma 2 model. This research not only advances the understanding of LLM security but also offers valuable insights for improving safety mechanisms in artificial intelligence systems.

AAAI 2025

Assessing Vulnerabilities in State-of-the-Art Large Language Models Through Hex Injection (Student Abstract)

The 15th Joint MMM-INTERMAG Conference (2022 Joint) is sponsored jointly by AIP Publishing and the IEEE Magnetics Society. Members of the international scientific and engineering communities interested in recent developments in fundamental and applied magnetism are invited to attend and contribute to the technical sessions. The technical program will include invited and contributed papers in oral and poster sessions, invited symposia, a plenary session, and an evening session, with about 1500 presentations overall. This Conference provides an outstanding opportunity for worldwide participants to meet their colleagues and collaborators and discuss developments in all areas of magnetism research.

The 2022 Joint Conference will offer both in-person and prerecorded on-demand content.

For tickets to the event, please register at the following link: https://magnetism.org/register

Please register for the Joint MMM-Intermag conference to join the event.

2022 Joint MMM-INTERMAG

This Conference provides an outstanding opportunity for worldwide participants to meet their colleagues and collaborators and discuss developments in all areas of magnetism research.

State-of-the-art large language models (LLMs) are designed with robust safeguards to prevent the disclosure of harmful information and dangerous procedures. However, "jailbreaking" techniques can circumvent these protections by exploiting vulnerabilities in the models. This paper introduces a novel method, Hex Injection, which leverages a specific weakness in LLMs' ability to decode encoded text to uncover concealed dangerous instructions. Hex Injection distinguishes itself from traditional methods by combining encoded instructions with plaintext prompts to reveal unsafe content more effectively. Our approach involves encoding potentially malicious prompts in hexadecimal and integrating them. We observe a 94% average success rate (ASR) with a combination of plaintext, encoded, and role-play for Llama 3 and 3.1 models, and an 86% ASR for the Gemma 2 model. This research not only advances the understanding of LLM security but also offers valuable insights for improving safety mechanisms in artificial intelligence systems.

poster

We are pleased to announce the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), which will be held in Philadelphia, Pennsylvania at the Pennsylvania Convention Center from February 25 to March 4, 2025.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

### [Invited Speakers](https://aaai.org/conference/aaai/aaai-25/aaai-25-invited-speakers/)

Register [here](https://aaai.org/conference/aaai/aaai-25/registration/)

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.



In federated learning, frequent parameter transmission between clients and the server results in significant communication overhead, particularly due to redundancy within the parameters. To address this issue, we propose a Complementary Pruning for Device-to-Device Communication (FedCPD) method. This approach effectively reduces the amount of transmitted parameters by applying complementary pruning techniques on both the server and clients. Additionally, we decrease the communication frequency between clients and the server by employing chain updates among clients (i.e., device-to-device communication). We conducted experiments on the MNIST, FMNIST, CIFAR-10, and CIFAR-100 datasets, and the results demonstrate that our method significantly reduces communication costs while improving model accuracy.

A High-Efficiency Federated Learning Method Using Complementary Pruning for D2D Communication (Student Abstract)

Top-one recommendation with anonymous user behaviors, also known as session-based recommendation (SBR), faces challenges of top-one ranking and short anonymous sequences. To this end, we propose a novel objective that combines (1) a reciprocal rank loss to directly optimize the benchmark metric of top-one recommendation, with (2) a listwise contrastive loss to handle short sequences through listwise augmented consistency regularization. Empirical studies demonstrate that optimizing the proposed objective significantly improves the performance of existing SBR baselines.

Top-one Recommendation with Anonymous User Behaviors (Student Abstract)

Ocean exploration requires effective collaboration between the unmanned surface vehicle (USV) and autonomous underwater vehicles (AUVs). We propose UACOF, a USV-AUV collaboration framework that enhances multi-AUV performance under extreme sea conditions. The framework includes high-precision multi-AUV location via USV path planning with Fisher information matrix optimization and reinforcement learning training for cooperative tasks. Experimental results show UACOF's superior feasibility, performance, coordination and robustness in extreme conditions.

UACOF: A USV-AUV Collaboration Framework for Underwater Tasks Under Extreme Sea Conditions (Student Abstract)

In this student paper, we report on our project to enhance road safety in South Carolina (SC) by analyzing traffic data provided by the Department of Transportation and evaluating the impact of a school-level student driver education program called Alive@25. We improve the understanding of road safety using these traffic and training data to understand collision patterns and areas for improvement and assess training coverage gaps. Our approach combines geospatial analysis, economic impact assessment, temporal trend analysis, and interactive visualizations while leveraging AI techniques to clean and analyze extensive datasets. Key findings revealed higher collision rates in urban counties and rising collision rates in mostly rural areas, where Alive@25 participation is declining. These insights led to recommendations for improving road infrastructure and expanding safety training programs. This research demonstrates the potential of AI-driven insights to inform timely, cost-effective interventions and promote multi-stakeholder engagement in addressing public safety challenges while teaching students data science and AI skills and civic engagement.

Towards Enhancing Road Safety in South Carolina Using Insights from Traffic and Driver-Education Data (Student Abstract)

We propose the Next Sentence Prediction (NSP) task as a simple, objective, scalable, automated way to test ChatGPT’s text comprehension. Given a context excerpted from a children’s story, the task is to distinguish the next story sentence from a later sentence in the story. We analyze how ChatGPT’s performance on this task is related to various features of the text, using data from English and Swahili children’s stories.

Using Next Sentence Prediction to Test ChatGPT’s Text Comprehension (Student Abstract)

In recent years, reinforcement learning has been widely applied in the field of games. However, most studies focus on assisting agents to achieve victory, with less attention paid to whether the agents exhibit human-like characteristics. In order to build human-like agents with high performance, we propose a method for learning the strategies of human players in modern three-dimensional video games. Our method utilizes a hierarchical framework, learning basic behaviors and intentions of human players at the lower level through imitation learning, and generalized policies at the high level through reinforcement learning. Compared with other existing methods, our method demonstrates significant advantages in learning human-like strategies in complex environments.

Towards Building Human-like Smart Agents in Modern 3D Video Games (Student Abstract)

Increasing student populations and diverse course offerings have led to perceived inequities in U.S. high school course scheduling. Traditional integer programming (IP) methods for the High School Scheduling Problem (HSSP) fail to address these fairness concerns. This research introduces the Fair High School Scheduling Problem (FHSSP), an extension of the HSSP that incorporates student preferences and fairness principles from market design. We develop an IP model to generate course schedules that are both feasible and equitable. Tested on real course request data from a California high school, our model successfully produces schedules that ensure fairness without compromising feasibility. These results demonstrate the potential of our approach to enhance fairness in high school scheduling and its applicability to various real-world scheduling challenges. Additionally, this study highlights the feasibility of integrating human preferences and emotions into mathematical models, promoting more inclusive and balanced allocation systems.

High School Course Scheduling: Student Preferences and Fairness Constraints (Student Abstract)

Causal Inference (CI) plays a crucial role in building unbiased recommender systems. However, most current CI-based debiasing methods only pay attention on either popularity bias or conformity bias. This paper presents a Disentangled Counterfactual Reasoning framework to alleviate dual biases in recommendation, so called DCR. Concretely, we consider the impact of both item popularity and user conformity during training, and separate their indirect effects by disentangling user and item embeddings into biased and unbiased components. In the inference stage, we perform counterfactual reasoning to simultaneously mitigate the indirect and direct effects of bias factors. Experimental results demonstrate the effectiveness of our DCR.

Alleviating Dual Biases in Recommendation (Student Abstract)

A vast amount of textual data is added to the internet daily, making utilization and interpretation of textual data difficult and cumbersome.
As a result, automatic text summarization is crucial for extracting relevant information, saving precious time.
Although many transformer models excel in summarization, they are constrained by their input size, preventing them from processing texts longer than their context size.
This study introduces several novel algorithms that allow any LLM to efficiently overcome its input size limitation, effectively utilizing its full potential without any architectural modifications.
We test our algorithms on texts with more than 70,000 words, and our experiments show a significant increase in BERTScore with competitive ROUGE scores.

Automatic Summarization of Long Documents (Student Abstract)

In the rapidly advancing field of AI-assisted medical diagnosis, the generation of medical reports for Chest X-rays (CXR) has significantly improved with the increased availability of radiographs and their corresponding reports. However, these reports often contain complex medical terminology, making them difficult for patients and non-healthcare professionals to understand. In this study, we introduce a strategy called Chained Prompting for Improved Readability of Medical Reports (CPIR-MR), which translates original medical reports into more comprehensible language. Our primary contribution is the creation of a new extension to the IU X-Ray dataset, providing Simplified Medical Reports (SMRs) generated by CPIR-MR. Additionally, we demonstrate that standard methodologies can effectively produce these simplified reports by proposing a multi-modal text decoder (MTD) that combines BLIP with a classification network to generate simplified medical explanations (SMEs) when fine-tuned on SMRs.

Downloads

Next from AAAI 2025

A High-Efficiency Federated Learning Method Using Complementary Pruning for D2D Communication (Student Abstract)

Similar lecture

12/10 Switched Reluctance Motor with a Hex Connection