Keynote Panel
CAMLIS
Keynote Panel
28:48
AdapterSwap: Continuous Training of LLMs with Data Removal and Access-Control Guarantees
CAMLIS
AdapterSwap: Continuous Training of LLMs with Data Removal and Access-Control Guarantees
29:11
Defending Large Language Models Against Attacks With Residual Stream Activation Analysis
CAMLIS
Defending Large Language Models Against Attacks With Residual Stream Activation Analysis
23:33
LLM Backdoor Activations Stick Together
CAMLIS
LLM Backdoor Activations Stick Together
20:40
Curl: Private LLMs through Wavelet-Encoded Look-Up Tables
CAMLIS
Curl: Private LLMs through Wavelet-Encoded Look-Up Tables
19:49
Hamm-Grams: Mining Common Regular Expressions via Locality Sensitive Hashing
CAMLIS
Hamm-Grams: Mining Common Regular Expressions via Locality Sensitive Hashing
19:12
Let’s Make it Personal: Customizing Threat Intelligence with Metric Learning
CAMLIS
Let’s Make it Personal: Customizing Threat Intelligence with Metric Learning
25:39
Defending Against Indirect Prompt Injection Attacks With Spotlighting
CAMLIS
Defending Against Indirect Prompt Injection Attacks With Spotlighting
26:16
Keynote - Acting to Ensure AI Benefits Cyber Defense in a Decade of Technological Surprise
CAMLIS
Keynote - Acting to Ensure AI Benefits Cyber Defense in a Decade of Technological Surprise
1:07:59
Is F1 Score Suboptimal for Cybersecurity Models? Introducing Cscore
CAMLIS
Is F1 Score Suboptimal for Cybersecurity Models? Introducing Cscore
28:15
Structure and Semantics-Aware Malware Classification with Vision Transformers
CAMLIS
Structure and Semantics-Aware Malware Classification with Vision Transformers
28:24
PEVuln: A Benchmark Dataset for Using Machine Learning to Detect Vulnerabilities in PE Malware
CAMLIS
PEVuln: A Benchmark Dataset for Using Machine Learning to Detect Vulnerabilities in PE Malware
14:58
DIP-ECOD: Improving Anomaly Detection in Multimodal Distributions
CAMLIS
DIP-ECOD: Improving Anomaly Detection in Multimodal Distributions
21:05
LLM Agents for Vulnerability Identification and Verification of CVEs
CAMLIS
LLM Agents for Vulnerability Identification and Verification of CVEs
31:58
End-to-End Framework using LLMs for Technique Identification and Threat-Actor Attribution
CAMLIS
End-to-End Framework using LLMs for Technique Identification and Threat-Actor Attribution
29:34
Towards Autonomous Cyber-Defence: Using Co-Operative Decision Making for Cybersecurity
CAMLIS
Towards Autonomous Cyber-Defence: Using Co-Operative Decision Making for Cybersecurity
26:07
PyRIT: A Framework for Security Risk Identification and Red Teaming in Generative AI Systems
CAMLIS
PyRIT: A Framework for Security Risk Identification and Red Teaming in Generative AI Systems
20:33
Cybersecurity and Infrastructure Security Agency (CISA)
CAMLIS
Cybersecurity and Infrastructure Security Agency (CISA)
52:00
Graph-Based User-Entity Behavior Analytics for Enterprise Insider Threat Detection
CAMLIS
Graph-Based User-Entity Behavior Analytics for Enterprise Insider Threat Detection
26:47
Don’t you forget NLP: prompt injection using repeated sequences in ChatGPT
CAMLIS
Don’t you forget NLP: prompt injection using repeated sequences in ChatGPT
26:34
Playing Defense: Benchmarking Cybersecurity Capabilities of Large Language Models
CAMLIS
Playing Defense: Benchmarking Cybersecurity Capabilities of Large Language Models
28:11
LLM Prompt Injection: Attacks and Defenses
CAMLIS
LLM Prompt Injection: Attacks and Defenses
22:00
Model Leeching: An Extraction Attack Targeting LLMs
CAMLIS
Model Leeching: An Extraction Attack Targeting LLMs
28:09
Anomaly Detection of Command Shell Sessions based on DistilBERT: Unsupervised and Supervised Appro
CAMLIS
Anomaly Detection of Command Shell Sessions based on DistilBERT: Unsupervised and Supervised Appro
17:51
Razing to the Ground Machine Learning Phishing Webpage Detectors with Query Efficient Adversarial HT
CAMLIS
Razing to the Ground Machine Learning Phishing Webpage Detectors with Query Efficient Adversarial HT
25:51
Web content filtering through knowledge distillation of Large Language Models
CAMLIS
Web content filtering through knowledge distillation of Large Language Models
20:30
Compilation as a Defense: Enhancing DL Model Attack Robustness via Tensor Optimization
CAMLIS
Compilation as a Defense: Enhancing DL Model Attack Robustness via Tensor Optimization
23:35
Multi-Agent Reinforcement Learning for Maritime Operational Technology Cyber Security
CAMLIS
Multi-Agent Reinforcement Learning for Maritime Operational Technology Cyber Security
25:25
Enhancing Exfiltration Path Analysis Using Reinforcement Learning
CAMLIS
Enhancing Exfiltration Path Analysis Using Reinforcement Learning
25:49
Keynote - Security Issues in Generative AI
CAMLIS
Keynote - Security Issues in Generative AI
1:11:02
MalDICT: Benchmark Datasets on Malware Behaviors, Platforms, Exploitation, and Packers
CAMLIS
MalDICT: Benchmark Datasets on Malware Behaviors, Platforms, Exploitation, and Packers
25:23
Keynote - Lessons for AI Security Preparedness
CAMLIS
Keynote - Lessons for AI Security Preparedness
1:07:58
Adaptive Experimental Design for Intrusion Data Collection
CAMLIS
Adaptive Experimental Design for Intrusion Data Collection
25:59
Proxy in a Haystack: Uncovering and Classifying MFA Bypass Phishing Attacks in Large Scale Authenti
CAMLIS
Proxy in a Haystack: Uncovering and Classifying MFA Bypass Phishing Attacks in Large Scale Authenti
24:17
Small Effect Sizes in Malware Detection? Make Harder Train:Test Splits!
CAMLIS
Small Effect Sizes in Malware Detection? Make Harder Train:Test Splits!
24:25
SQL Driven Infrastructure for Cybersecurity ML Operations
CAMLIS
SQL Driven Infrastructure for Cybersecurity ML Operations
25:54
FASER: Binary Code Similarity Search through the use of Intermediate Representations
CAMLIS
FASER: Binary Code Similarity Search through the use of Intermediate Representations
23:57
Threat Detection on Kubernetes Logs Using GNN Embeddings
CAMLIS
Threat Detection on Kubernetes Logs Using GNN Embeddings
27:11
Building a Multi-Tenant Machine Learning Workflow Orchestration Platform (CAMLIS 2022)
CAMLIS
Building a Multi-Tenant Machine Learning Workflow Orchestration Platform (CAMLIS 2022)
17:12
OmnibusCyber: a schema-ready strongly typed database to model all cyber security objects
CAMLIS
OmnibusCyber: a schema-ready strongly typed database to model all cyber security objects
14:41
Inroads in Autonomous Network Defence using Explained Reinforcement Learning (CAMLIS 2022)
CAMLIS
Inroads in Autonomous Network Defence using Explained Reinforcement Learning (CAMLIS 2022)
19:19
Enhancing 2FA with IP-based geolocation without blocking all your users (CAMLIS 2022)
CAMLIS
Enhancing 2FA with IP-based geolocation without blocking all your users (CAMLIS 2022)
11:42
Playing Cat and Mouse with the Attacker: Frequent Item Set Mining in the Registry (CAMLIS 2022)
CAMLIS
Playing Cat and Mouse with the Attacker: Frequent Item Set Mining in the Registry (CAMLIS 2022)
20:06
Firenze: Model Evaluation Using Weak Signals (CAMLIS 2022)
CAMLIS
Firenze: Model Evaluation Using Weak Signals (CAMLIS 2022)
19:59
Keys to the Digital Castle: Detecting Malicious MDA Device Enrollment at Scale (CAMLIS 2022)
CAMLIS
Keys to the Digital Castle: Detecting Malicious MDA Device Enrollment at Scale (CAMLIS 2022)
8:43
Temporal Attack Detection in Multimodal Cyber-Physical Systems with Sticky HDP-HMM (CAMLIS 2022)
CAMLIS
Temporal Attack Detection in Multimodal Cyber-Physical Systems with Sticky HDP-HMM (CAMLIS 2022)
11:39
Keynote: Lessons Learned in Red Teaming AI Systems in High-Stakes Environments (CAMLIS 2022)
CAMLIS
Keynote: Lessons Learned in Red Teaming AI Systems in High-Stakes Environments (CAMLIS 2022)
36:48
Half-Day Vulnerabilities: A Study of the First Days of CVE Entries (CAMLIS 2022)
CAMLIS
Half-Day Vulnerabilities: A Study of the First Days of CVE Entries (CAMLIS 2022)
21:38
An Explainable Framework for Predicting Vulnerability Threat Using Topic and Threat Modeling
CAMLIS
An Explainable Framework for Predicting Vulnerability Threat Using Topic and Threat Modeling
18:29
ARNIE: Hasta La Vector, Baby! Towards Better Encoding and Vectorization of Cyber Artifacts
CAMLIS
ARNIE: Hasta La Vector, Baby! Towards Better Encoding and Vectorization of Cyber Artifacts
26:16
Network Security Modelling with Distributional Data (CAMLIS 2022)
CAMLIS
Network Security Modelling with Distributional Data (CAMLIS 2022)
19:30
Detecting Homoglyph Domains with Character Image LSTMs (CAMLIS 2022)
CAMLIS
Detecting Homoglyph Domains with Character Image LSTMs (CAMLIS 2022)
16:44
Learning to Embed Byte Sequences with Convolutional Autoencoders (CAMLIS 2022)
CAMLIS
Learning to Embed Byte Sequences with Convolutional Autoencoders (CAMLIS 2022)
20:50
Keynote: PE Binary Classification Pitfalls (CAMLIS 2022)
CAMLIS
Keynote: PE Binary Classification Pitfalls (CAMLIS 2022)
38:25
Heterogenous Graph Embedding for Malicious Azure Sign-in Detection (CAMLIS 2022)
CAMLIS
Heterogenous Graph Embedding for Malicious Azure Sign-in Detection (CAMLIS 2022)
17:01
Webshell Detection Case Study (CAMLIS 2022)
CAMLIS
Webshell Detection Case Study (CAMLIS 2022)
22:49
Minimizing Compute Costs: When When Should We Run More Expensive Malware Analysis? (CAMLIS 2022)
CAMLIS
Minimizing Compute Costs: When When Should We Run More Expensive Malware Analysis? (CAMLIS 2022)
22:03
Efficient Malware Analysis Using Metric Embeddings (CAMLIS 2022)
CAMLIS
Efficient Malware Analysis Using Metric Embeddings (CAMLIS 2022)
19:25
TweetSeeker: Extracting Adversary Methods from the Twitterverse
CAMLIS
TweetSeeker: Extracting Adversary Methods from the Twitterverse
30:34
Next Generation Process Emulation with Binee
CAMLIS
Next Generation Process Emulation with Binee
29:09
Using Lexical Features for Malicious URL Detection- A Machine Learning Approach
CAMLIS
Using Lexical Features for Malicious URL Detection- A Machine Learning Approach
19:10
EMBER Improvements
CAMLIS
EMBER Improvements
27:21
An Information Security Approach to Feature Engineering
CAMLIS
An Information Security Approach to Feature Engineering
15:10
Learning to Rank Relevant Malware Strings Using Weak Supervision
CAMLIS
Learning to Rank Relevant Malware Strings Using Weak Supervision
26:56
On Evaluating Adversarial Robustness
CAMLIS
On Evaluating Adversarial Robustness
50:32
Scalable Infrastructure for Malware Labeling and Analysis
CAMLIS
Scalable Infrastructure for Malware Labeling and Analysis
32:27
Mitigating Adversarial Attacks against Machine Learning for Static Analysis
CAMLIS
Mitigating Adversarial Attacks against Machine Learning for Static Analysis
26:40
Towards a Trustworthy and Resilient Machine Learning Classifier - a Case Study of Ransomware Behavio
CAMLIS
Towards a Trustworthy and Resilient Machine Learning Classifier - a Case Study of Ransomware Behavio
26:44
Exploring Backdoor Poisoning Attacks Against Malware Classifiers
CAMLIS
Exploring Backdoor Poisoning Attacks Against Malware Classifiers
29:03
Trying to Make Meterpreter into an Adversarial Example
CAMLIS
Trying to Make Meterpreter into an Adversarial Example
28:16
Applying Deep Graph Representation Learning to the Malware Graph
CAMLIS
Applying Deep Graph Representation Learning to the Malware Graph
32:19
Applications of Graph Integration to Function Comparison and Malware Classification
CAMLIS
Applications of Graph Integration to Function Comparison and Malware Classification
31:06
What is the Shape of an Executable?
CAMLIS
What is the Shape of an Executable?
21:26
ProblemChild: Discovering Anomalous Patterns based on Parent-Child Process Relationships
CAMLIS
ProblemChild: Discovering Anomalous Patterns based on Parent-Child Process Relationships
29:42
Describing Malware via Tagging
CAMLIS
Describing Malware via Tagging
31:13
Protecting Users: When Security and Privacy Collide
CAMLIS
Protecting Users: When Security and Privacy Collide
34:37
Improved Multi-Stage Classification for Information Security Applications
CAMLIS
Improved Multi-Stage Classification for Information Security Applications
28:37
Automated in-memory malware/rootkit detection via binary analysis and machine learning
CAMLIS
Automated in-memory malware/rootkit detection via binary analysis and machine learning
27:06
TreeHuggr: Discovering where tree-based classifiers are vulnerable to adversarial attack
CAMLIS
TreeHuggr: Discovering where tree-based classifiers are vulnerable to adversarial attack
27:10
Estimating uncertainty for binary classifiers
CAMLIS
Estimating uncertainty for binary classifiers
30:56
Using Anomaly Detection on User Demographic Distributions to Identify Fake Account Bursts
CAMLIS
Using Anomaly Detection on User Demographic Distributions to Identify Fake Account Bursts
29:23
Point process modeling of temporal patterns in user authentication behavior
CAMLIS
Point process modeling of temporal patterns in user authentication behavior
30:27
Some Mistakes are More Mistaken Than Others: Using Cost-Matrix Clustering to Address Misclassificati
CAMLIS
Some Mistakes are More Mistaken Than Others: Using Cost-Matrix Clustering to Address Misclassificati
29:56
Do You Know What Your ML Is Doing?
CAMLIS
Do You Know What Your ML Is Doing?
44:26
Interpretation of Threat Prediction Model for SOC Analysts
CAMLIS
Interpretation of Threat Prediction Model for SOC Analysts
28:32
Measure Twice, Quarantine Once: A Tale of Malware Labeling over Time
CAMLIS
Measure Twice, Quarantine Once: A Tale of Malware Labeling over Time
27:40
An Effective Framework for Malware Detection and Classification using Feature Prioritization
CAMLIS
An Effective Framework for Malware Detection and Classification using Feature Prioritization
19:43
Activation Analysis of a Byte-based Deep Neural Network for Malware Classification
CAMLIS
Activation Analysis of a Byte-based Deep Neural Network for Malware Classification
30:07
Labeling Red: Harvesting Labeled Data from Adversary Simulations
CAMLIS
Labeling Red: Harvesting Labeled Data from Adversary Simulations
32:44
Worm2Vec: Embedding Malicious Code for Efficient Clustering & Classification
CAMLIS
Worm2Vec: Embedding Malicious Code for Efficient Clustering & Classification
28:56
Datasets for the Everyman
CAMLIS
Datasets for the Everyman
26:03
Serverless Data Processing Architecture for Binary Analysis
CAMLIS
Serverless Data Processing Architecture for Binary Analysis
21:37
Inferring Model Families from Deployed Black Boxes
CAMLIS
Inferring Model Families from Deployed Black Boxes
28:56
APTinder: An optimized approach for finding that perfect APT match
CAMLIS
APTinder: An optimized approach for finding that perfect APT match
28:36
A feature presentation: semi-supervised learning of file representations
CAMLIS
A feature presentation: semi-supervised learning of file representations
27:29
Anticipatory Cyber Defense via Predictive Analytics, Machines Learning and Simulation
CAMLIS
Anticipatory Cyber Defense via Predictive Analytics, Machines Learning and Simulation
29:35
Bonware to the Rescue: the Future Autonomous Cyber Defense Agents | Dr Alexander Kott | CAMLIS 2018
CAMLIS
Bonware to the Rescue: the Future Autonomous Cyber Defense Agents | Dr Alexander Kott | CAMLIS 2018
44:41