Skip to content

Commit 2cfb5d8

Browse files
author
Zihan Wang
committed
publication update
1 parent ff5fc89 commit 2cfb5d8

File tree

8 files changed

+48
-11
lines changed

8 files changed

+48
-11
lines changed

‎content/publications/aim.md‎

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,9 @@
1+
+++
2+
title = "Model Modulation with Logits Redistribution"
3+
date = 2025-03-01
4+
5+
[extra]
6+
author = "Zihan Wang, Zhongkui Ma, Xinguo Feng, Zhiyang Mei, Zhiyong Ma, Derui Wang, Minhui Xue, Guangdong Bai"
7+
target = "The Web Conference (WWW), 2025."
8+
pdf = ""
9+
+++

‎content/publications/chuan25www.md‎

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,9 @@
1+
+++
2+
title = "Understanding and Detecting File Knowledge Leakage in GPT App Ecosystem"
3+
date = 2025-03-01
4+
5+
[extra]
6+
author = "Chuan Yan, Bowei Guan, Yazhi Li, Mark Huasong Meng, Liuhuo Wan, Guangdong Bai"
7+
target = "The Web Conference (WWW), 2025."
8+
pdf = ""
9+
+++

‎content/publications/coover-www.md‎

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,9 @@
1+
+++
2+
title = "Understanding and Detecting File Knowledge Leakage in GPT App Ecosystem"
3+
date = 2025-03-01
4+
5+
[extra]
6+
author = "Baiqi Chen, Jiawei Lyu, Tingming Wu, Mohan Baruwal Chhetri, Guangdong Bai"
7+
target = "The Web Conference (WWW), 2025."
8+
pdf = ""
9+
+++

‎content/publications/corelocker.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,6 +4,6 @@ date = 2024-03-09
44

55
[extra]
66
author = "Zihan Wang, Zhongkui Ma, Xinguo Feng, Ruoxi Sun, Hu Wang, Minhui Xue, Guangdong Bai"
7-
target = "45th IEEE Symposium on Security and Privacy (IEEE S&P), 2024."
7+
target = "IEEE Symposium on Security and Privacy (Oakland), 2024."
88
pdf = "https://www.zihan.com.au/assets/files/SP24CoreLocker.pdf"
99
+++

‎content/publications/modx-sp.md‎

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,9 @@
1+
+++
2+
title = "Modifier Unlocked: Jailbreaking Text-to-Image Models Through Prompts"
3+
date = 2025-03-12
4+
5+
[extra]
6+
author = "Shuofeng Liu, Mengyao Ma, Minhui Xue, Guangdong Bai"
7+
target = "IEEE Symposium on Security and Privacy (Oakland), 2025."
8+
pdf = ""
9+
+++

‎templates/index.html‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -26,7 +26,7 @@ <h4 class="title is-4 my-2">About us</h4>
2626
TrustLab's primary objective is to develop theories, techniques, and systems that can ensure the trustworthiness of complex software and intelligence systems.
2727
It strives to enhance security, robustness and reliability of software and intelligence systems, and make them more trustworthy for the individuals and organizations that rely on them.</p>
2828
</div>
29-
<div class="column is-4">
29+
<!-- <div class="column is-4">
3030
<div class="panel is-uq-light">
3131
<p class="panel-heading">
3232
Latest News
@@ -47,7 +47,7 @@ <h4 class="title is-4 my-2">About us</h4>
4747
</a>
4848
{% endfor %}
4949
</div>
50-
</div>
50+
</div> -->
5151
</div>
5252
</section>
5353

‎templates/navbar.html‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -13,13 +13,13 @@
1313

1414
<div id="navbarMenu" class="navbar-menu">
1515
<div class="navbar-start">
16-
<a class="navbar-item" href="/news/">
16+
<!-- <a class="navbar-item" href="/news/">
1717
<span class="icon-text">
1818
<span class="icon">
1919
<i class="fa-solid fa-calendar-day"></i>
2020
</span>
2121
<span>News</span>
22-
</a>
22+
</a> -->
2323

2424
<a class="navbar-item" href="/publications/">
2525
<span class="icon-text">

‎templates/projects.html‎

Lines changed: 7 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -6,11 +6,12 @@
66
<section class="section container">
77
<!-- <h1 class="title is-3" style="text-align: left; font-size: 2.5em;">TrustLab Projects (SEC4AI, AI4SEC)</h1> -->
88
<h1 class="title is-3" style="text-align: left; font-size: 2.5em;">
9-
TrustLab Projects (<span style="color: #b44695;">Security4AI</span>, <span style="color: #4682B4;">AI4Security</span>)
9+
<!-- TrustLab Projects (<span style="color: #b44695;">Security4AI</span>, <span style="color: #4682B4;">AI4Security</span>) -->
10+
TrustLab Projects
1011
</h1>
11-
<div style="text-align: center; margin-top: -3em; margin-bottom: -3em;">
12+
<!-- <div style="text-align: center; margin-top: -3em; margin-bottom: -3em;">
1213
<img src="https://raw.githubusercontent.com/UQ-Trust-Lab/UQ-Trust-Lab.github.io/master/static/covers/trustlab.svg" alt="" width="100%">
13-
</div>
14+
</div> -->
1415
<br><br>
1516
<!-- <p style="background-color: #E6E6FA; padding: 10px;">
1617
Hi ALL, <br>
@@ -31,10 +32,10 @@ <h1 class="title is-3" style="text-align: left; font-size: 2.5em;">
3132
<br>
3233
Zihan
3334
</p> -->
34-
<a href="/projects/project1/" style="font-size: 1.5em; font-weight: bold; color: #b44695;">Trustworthy and Responsible AI
35+
<a href="/projects/project1/" style="font-size: 1.5em; font-weight: bold; color: #b44695;">Trustworthy and Responsible ML
3536
</a>
3637
<br>
37-
<p>Trustworthy and Responsible AI is about building AI systems that operate reliably and ethically, aligning with societal values and expectations. Ensuring that these systems behave as expected under various conditions is essential to minimize the risk of unintended outcomes. Equally important is controlling how AI models are used, ensuring they adhere to specific guidelines and are not misapplied. Moreover, it's crucial to maintain a clear focus on the intended purposes of these models, preventing their use in ways that could lead to ethical or legal concerns. By integrating these principles, AI systems can be developed and deployed in a manner that is both reliable and responsible.
38+
<p>Trustworthy and Responsible ML is about building ML systems that operate reliably and ethically, aligning with societal values and expectations. Ensuring that these systems behave as expected under various conditions is essential to minimize the risk of unintended outcomes. Equally important is controlling how ML models are used, ensuring they adhere to specific guidelines and are not misapplied. Moreover, it's crucial to maintain a clear focus on the intended purposes of these models, preventing their use in ways that could lead to ethical or legal concerns. By integrating these principles, ML systems can be developed and deployed in a manner that is both reliable and responsible.
3839
</p>
3940
<br>
4041

@@ -53,7 +54,7 @@ <h1 class="title is-3" style="text-align: left; font-size: 2.5em;">
5354
</p>
5455
<br>
5556

56-
<a href="/projects/project4/" style="font-size: 1.5em; font-weight: bold; color: #4682B4;">AI for Software Engineering</a>
57+
<a href="/projects/project4/" style="font-size: 1.5em; font-weight: bold; color: #4682B4;">ML for Software Engineering</a>
5758
<br>
5859
<p>TrustLab has conducted in-depth and systematic research primarily on Web-based collaboration platforms, Deep Learning libraries, and the emerging third-party applications integrated with LLMs. Our rigorous defect testing has particularly focused on these platforms' performance in complex scenarios such as permission invocation, memory consumption, computational errors, data transmission, and secure API calls. Our research not only uncovers high-risk vulnerabilities hidden within these systems but also provides specific recommendations for improvement. These insights serve as valuable guidance for developers and engineers, helping them optimize system design and enhance software security and robustness.
5960
</p>

0 commit comments

Comments
 (0)